A Stochastic Approximation Method

1951/09/01 by Herbert Robbins, Sutton Monro · 9,641 citations
Decision Sciences · Mathematics · #Alpha (finance) #Applied mathematics #Combinatorics #Computer science #Constant (computer programming) #Expected value #Function (biology) #Geometry #Mathematics #Monotone polygon #Optimal Experimental Design Methods #Statistics #Value (mathematics)

paper · pdf · doi:10.1214/aoms/1177729586

published in The Annals of Mathematical Statistics 22(3), 400-407 (Institute of Mathematical Statistics)

openalex publication_date 1951/09/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

Let M(x) denote the expected value at level x of the response to a certain experiment. M(x) is assumed to be a monotone function of x but is unknown to the experimenter, and it is desired to find the solution x = θ of the equation M(x) = α, where α is a given constant. We give a method for making successive experiments at levels x₁,x₂,⋯ in such a way that x_n will tend to θ in probability.

Cited by

• Semimartingale Stochastic Approximation Procedures and Recursive Estimation
• Stochastic Estimation of the Maximum of a Regression Function
• PyPose: A Library for Robot Learning with Physics-based Optimization
• The Modern Mathematics of Deep Learning
• Stochastic optimization on matrices and a graphon McKean–Vlasov limit
• PYPM-GGD: Pitman-Yor Process Mixture with Generalized Gaussian Density using ADAM
• Advances in Asynchronous Parallel and Distributed Optimization
• An information field theory approach to Bayesian state and parameter estimation in dynamical systems
• Accurate computation of quantum excited states with neural networks
• A Nonparametric Approach to Pricing and Hedging Derivative Securities Via Learning Networks
• Mini-batch stochastic approximation methods for nonconvex stochastic composite optimization
• Sample size selection in optimization methods for machine learning
• Analysis of biased stochastic gradient descent using sequential semidefinite programs
• Green behavior propagation analysis based on statistical theory and intelligent algorithm in data-driven environment
• Distributed stochastic gradient tracking methods
• Convergence of Random Batch Method with replacement for interacting particle systems
• Fitting the psychometric function
• A Lyapunov Theory for Finite-Sample Guarantees of Markovian Stochastic Approximation
• Pricing Under Uncertainty in Multi-Interval Real-Time Markets
• Calibrated Bayesian Nonparametric Tolerance Intervals
• Proximity and the Evolution of Collaboration Networks: Evidence from Research and Development Projects within the Global Navigation Satellite System (GNSS) Industry
• A Deep Learning Algorithm for High-Dimensional Exploratory Item Factor Analysis
• GREEN: A lightweight architecture using learnable wavelets and Riemannian geometry for biomarker exploration with EEG signals
• Closed-Loop Knowledge Dynamics: An Operational Framework for Saturation and Escape
• Efficient Risk Estimation for the Credit Valuation Adjustment
• In-Run Data Shapley for Adam Optimizer
• Finite-horizon quantile martingale posteriors: raw-urn laws and matrix-gain regression
• Frictional Q-Learning
• Equilibrium Computation in Extensive-Form Games with Stochastic Action Sets
• Computing Equilibria in Games with Stochastic Action Sets
• Theoretical guarantees for stochastic gradient sampling methods via Gaussian convolution inequalities
• DiLLSUE: a differentiable GPU solver for link-based logit stochastic user equilibrium
• Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments
• From Atoms to Entropy: Optimal Noise Allocation for Diffusion Training in the Convex Regime
• Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation Is Wasteful
• Distillation of atomistic foundation models across architectures and chemical domains
• Vulnerability Detection via Multiple-Graph-Based Code Representation
• Fast Inference for Intractable Likelihood Problems using Variational Bayes
• Learning Equilibrium Play for Stochastic Parallel Gaussian Interference Channels
• A Federated Data-Driven Evolutionary Algorithm for Expensive Multi/Many-objective Optimization
• Numerical methods in large-scale optimization: inexact oracle and primal-dual analysis
• Adaptive Periodic Averaging: A Practical Approach to Reducing Communication in Distributed Learning
• Distributed Weight Consolidation: A Brain Segmentation Case Study
• Geometric Insights into the Convergence of Nonlinear TD Learning
• Adaptive Gradient Method with Resilience and Momentum
• A Cross Entropy based Optimization Algorithm with Global Convergence Guarantees
• Reinforcement Learning for Matrix Computations: PageRank as an Example
• The Statistics of Streaming Sparse Regression
• Optimal Transport Based Distributionally Robust Optimization: Structural Properties and Iterative Schemes
• An averaged projected Robbins-Monro algorithm for estimating the parameters of a truncated spherical distribution
• VR-SGD: A Simple Stochastic Variance Reduction Method for Machine Learning
• Learning Machines Implemented on Non-Deterministic Hardware
• Generative Max-Mahalanobis Classifiers for Image Classification, Generation and More
• Variational Dropout and the Local Reparameterization Trick
• SI-ADMM: A Stochastic Inexact ADMM Framework for Stochastic Convex Programs
• ADADELTA: An Adaptive Learning Rate Method
• Why (and When and How) Contrastive Divergence Works
• DTN: A Learning Rate Scheme with Convergence Rate of O(1/t) for SGD
• An overview of gradient descent optimization algorithms
• Bend to Mend: Toward Trustworthy Variational Bayes with Valid Uncertainty Quantification
• Semantics, Representations and Grammars for Deep Learning
• Computing Pure-Strategy Nash Equilibria in a Two-Party Policy Competition: Existence and Algorithmic Approaches
• Painless step size adaptation for SGD
• Deep Neural Networks - A Brief History
• Training Neural Networks with an algorithm for piecewise linear functions
• Analysis of the Stochastic Alternating Least Squares Method for the Decomposition of Random Tensors
• A trust-region method for derivative-free nonlinear constrained stochastic optimization
• Stochastic Variance Reduction for Nonconvex Optimization
• Multilevel Monte Carlo Variational Inference
• Budgeted Training: Rethinking Deep Neural Network Training Under Resource Constraints
• Scale Weight Decay and Train Better
• Robust Training in High Dimensions via Block Coordinate Geometric Median Descent
• Adjusted Shuffling SARAH: Advancing Complexity Analysis via Dynamic Gradient Weighting
• An invitation to adaptive Markov chain Monte Carlo convergence theory
• tf.data: A Machine Learning Data Processing Framework
• Collapsed Variational Bayes Inference of Infinite Relational Model
• Sample Efficient Policy Gradient Methods with Recursive Variance Reduction
• A Projected Stochastic Gradient Method for Finite-Sum Problems with Linear Equality Constraints
• Efficient Online Conformal Selection with Limited Feedback
• Analyzing Process Data from Computer-Based Assessments: A Tutorial on Preprocessing, Feature Extraction, and Model-Based Inference
• Data relativistic uncertainty framework for low-illumination anime scenery image enhancement
• Investigating methods to solve large windfarm optimization problems with a minimum number of qubits using circuit-based quantum computers
• More Consistent Accuracy PINN via Alternating Easy-Hard Training
• Counterfactual Prediction with Deep Instrumental Variables Networks
• A Turn Toward Better Alignment: Few-Shot Generative Adaptation with Equivariant Feature Rotation
• Over-the-Air Goal-Oriented Communications
• Light and Widely Applicable MCMC: Approximate Bayesian Inference for Large Datasets
• Statistical Inference for Generative Models with Maximum Mean Discrepancy
• Training Neural Networks for and by Interpolation
• PhysMaster: Building an Autonomous AI Physicist for Theoretical and Computational Physics Research
• Learning General Policies with Policy Gradient Methods
• Fraud detection in credit card transactions using Quantum-Assisted Restricted Boltzmann Machines
• Finite-sample guarantees for data-driven forward-backward operator methods
• Beyond Sliding Windows: Learning to Manage Memory in Non-Markovian Environments
• Structural Reinforcement Learning for Heterogeneous Agent Macroeconomics
• Adaptive Accountability in Networked MAS: Tracing and Mitigating Emergent Norms at Scale
• Transfer Learning for Analysis of Collective and Non-Collective Thomson Scattering Spectra
• Smoothing DiLoCo with Primal Averaging for Faster Training of LLMs
• Exponentially weighted estimands and the exponential family: Filtering, prediction and smoothing
• Bias-Variance Trade-off for Clipped Stochastic First-Order Methods: From Bounded Variance to Infinite Mean
• Self-adaptive physics-informed neural network for forward and inverse problems in heterogeneous porous flow
• Non-strongly-convex smooth stochastic approximation with convergence rate O(1/n)
• Limit theorems for stochastic approximation algorithms
• A Stochastic Large-scale Machine Learning Algorithm for Distributed Features and Observations
• Statistical Inference for Model Parameters in Stochastic Gradient Descent
• Universality of high-dimensional scaling limits of stochastic gradient descent
• Stopping Rules for Stochastic Gradient Descent via Anytime-Valid Confidence Sequences
• Variational Inference for Fully Bayesian Hierarchical Linear Models
• Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections
• Multi-temporal Calving Front Segmentation
• Evolving Deep Learning Optimizers
• T-SKM-Net: Trainable Neural Network Framework for Linear Constraint Satisfaction via Sampling Kaczmarz-Motzkin Method
• Improved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex Optimization
• The Interplay of Statistics and Noisy Optimization: Learning Linear Predictors with Random Data Weights
• DS FedProxGrad: Asymptotic Stationarity Without Noise Floor in Fair Federated Learning
• On Synchronous, Asynchronous, and Randomized Best-Response Schemes for Stochastic Nash Games
• Robust equilibria in continuous games: From strategic to dynamic robustness
• Sampling from a log-concave distribution with Projected Langevin Monte Carlo
• Fast-feedback protocols for calibration and drift control in quantum computers
• Distribution-informed Online Conformal Prediction
• Control and Reinforcement Learning through the Lens of Optimization: An Algorithmic Perspective
• RVLF: A Reinforcing Vision-Language Framework for Gloss-Free Sign Language Translation
• Optimal and Diffusion Transports in Machine Learning
• A Perception CNN for Facial Expression Recognition
• Contextual Strongly Convex Simulation Optimization: Optimize then Predict with Inexact Solutions
• Greedy Alignment Principle for Optimizer Selection
• Evolutionary System 2 Reasoning: An Empirical Proof
• Noisy Memory Generates Value in Changing Environments
• Bayesian inference for hidden Markov models under genuine multimodality with application to ecological time series
• How (Mis)calibrated is Your Federated CLIP and What To Do About It?
• Statistical Analysis of Stationary Solutions of Coupled Nonconvex Nonsmooth Empirical Risk Minimization
• Safeguarded Stochastic Polyak Step Sizes for Non-smooth Optimization: Robust Performance Without Small (Sub)Gradients
• An hybrid stochastic Newton algorithm for logistic regression
• Random constraint sampling and duality for convex optimization
• Black Box Variational Inference
• State Dependent Performative Prediction with Stochastic Approximation
• Stochastic Online Optimization using Kalman Recursion
• Adversarial Training for Process Reward Models
• Optimal Rates for Learning with Nyström Stochastic Gradient Methods
• Online estimation of the asymptotic variance for averaged stochastic gradient algorithms
• AnoRefiner: Anomaly-Aware Group-Wise Refinement for Zero-Shot Industrial Anomaly Detection
• Global convergence rate analysis of unconstrained optimization methods based on probabilistic models
• Beyond Expectation: Concentration Inequalities for Randomized Iterative Methods
• Compositional Stochastic Average Gradient for Machine Learning and Related Applications
• MC² Mixed Integer and Linear Programming
• ROOT: Robust Orthogonalized Optimizer for Neural Network Training
• Solving Heterogeneous Agent Models with Physics-informed Neural Networks
• HVAdam: A Full-Dimension Adaptive Optimizer
• A Generalized Additive Partial-Mastery Cognitive Diagnosis Model
• Gradient Descent Algorithm Survey
• On the Fundamental Limit of the Stochastic Gradient Identification Algorithm Under Non-Persistent Excitation
• An iterative K-FAC algorithm for Deep Learning
• Adaptive SGD with Line-Search and Polyak Stepsizes: Nonconvex Convergence and Accelerated Rates
• Design Criteria for SGD Preconditioners: Local Conditioning, Noise Floors, and Basin Stability
• A Sufficient Condition for Convergences of Adam and RMSProp
• FedSKETCH: Communication-Efficient and Private Federated Learning via Sketching
• A Unified Convergence Analysis for Shuffling-Type Gradient Methods
• CrossJEPA: Cross-Modal Joint-Embedding Predictive Architecture for Efficient 3D Representation Learning from 2D Images
• OpenCML: End-to-End Framework of Open-world Machine Learning to Learn Unknown Classes Incrementally
• Bringing Stability to Diffusion: Decomposing and Reducing Variance of Training Masked Diffusion Models
• Distributed Delayed Stochastic Optimization
• Convergence and stability of Q-learning in Hierarchical Reinforcement Learning
• FairLRF: Achieving Fairness through Sparse Low Rank Factorization
• Towards Understanding Convergence and Generalization of AdamW
• Multimodal Continual Instruction Tuning with Dynamic Gradient Guidance
• Automated Machine Learning on Big Data using Stochastic Algorithm Tuning
• Memory Augmented Optimizers for Deep Learning
• NuBench: An Open Benchmark for Deep Learning-Based Event Reconstruction in Neutrino Telescopes
• Structure and Dynamics of Information Pathways in Online Media
• Stochastic Smoothing for Nonsmooth Minimizations: Accelerating SGD by Exploiting Structure
• Momentum Centering and Asynchronous Update for Adaptive Gradient Methods
• On the properties of variational approximations of Gibbs posteriors
• Debiasing Stochastic Gradient Descent to handle missing values
• Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses
• Momentum-based Accelerated Mirror Descent Stochastic Approximation for Robust Topology Optimization under Stochastic Loads
• Bayesian Imaging With Data-Driven Priors Encoded by Neural Networks: Theory, Methods, and Algorithms
• SMLSOM: The shrinking maximum likelihood self-organizing map
• Preconditioning Kernel Matrices
• Variational Bayesian Optimal Experimental Design
• On the convergence, lock-in probability and sample complexity of stochastic approximation
• Improving SGD convergence by online linear regression of gradients in\n multiple statistically relevant directions
• Logistic Q-Learning
• CAO: Curvature-Adaptive Optimization via Periodic Low-Rank Hessian Sketching
• Active Importance Sampling for Variational Objectives Dominated by Rare Events: Consequences for Optimization and Generalization
• Joint Stochastic Approximation and Its Application to Learning Discrete Latent Variable Models
• Optimising Density Computations in Probabilistic Programs via Automatic Loop Vectorisation
• Non-Euclidean SGD for Structured Optimization: Unified Analysis and Improved Rates
• Learning and Testing Convex Functions
• S-D-RSM: Stochastic Distributed Regularized Splitting Method for Large-Scale Convex Optimization Problems
• DKDS: A Benchmark Dataset of Degraded Kuzushiji Documents with Seals for Detection and Binarization
• Learning-based Bias Correction for Time Difference of Arrival Ultra-wideband Localization of Resource-constrained Mobile Robots
• Adaptive Hamiltonian Variational Integrators and Symplectic Accelerated Optimization
• A Class of Multi-particle Reinforced Interacting Random Walks
• On the Convergence of the Monte Carlo Exploring Starts Algorithm for Reinforcement Learning
• Online Covariance Matrix Estimation in Stochastic Gradient Descent
• Parallel and distributed asynchronous adaptive stochastic gradient methods
• A Linearly-Convergent Stochastic L-BFGS Algorithm
• Low-Rank Curvature for Zeroth-Order Optimization in LLM Fine-Tuning
• Spectral Gradient Descent Mitigates Anisotropy-Driven Misalignment: A Case Study in Phase Retrieval
• Numerical methods for the sign problem in Lattice Field Theory
• ODE approximation for the Adam algorithm: General and overparametrized setting
• Unified Theory of Adaptive Variance Reduction
• Stochastic simulation of partial discharge inception
• Functional central limit theorem for Euler--Maruyama scheme with decreasing step sizes
• A Lyapunov Theory for Finite-Sample Guarantees of Asynchronous Q-Learning and TD-Learning Variants
• Empirical evaluation of a Q-Learning Algorithm for Model-free Autonomous Soaring
• Modal Backflow Neural Quantum States for Anharmonic Vibrational Calculations
• No-Rank Tensor Decomposition Using Metric Learning
• Modeling Stellar Collisions in Galactic Nuclei Using Hydrodynamic Simulations and Machine Learning
• Trust-Region Methods with Low-Fidelity Objective Models
• Superpositional Gradient Descent: Harnessing Quantum Principles for Model Training
• Why Federated Optimization Fails to Achieve Perfect Fitting? A Theoretical Perspective on Client-Side Optima
• Exploring Landscapes for Better Minima along Valleys
• Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learning
• Learning Geometry: A Framework for Building Adaptive Manifold Models through Metric Optimization
• Convergence of off-policy TD(0) with linear function approximation for reversible Markov chains
• Analysis of Biased Stochastic Gradient Descent Using Sequential Semidefinite Programs
• Automatic Differentiation Variational Inference
• Scalable Perturbation Learning for Online Self-Supervised Learning in Echo State Networks
• BRAC+: Improved Behavior Regularized Actor Critic for Offline Reinforcement Learning
• Stochastic Conditional Gradient++
• An Adaptive Online HDP-HMM for Segmentation and Classification of Sequential Data
• Sharpness-aware Quantization for Deep Neural Networks
• GOAT: GPU Outsourcing of Deep Learning Training With Asynchronous Probabilistic Integrity Verification Inside Trusted Execution Environment
• Overdispersed Black-Box Variational Inference
• The Variational Gaussian Process
• Voice Biometrics Security: Extrapolating False Alarm Rate via Hierarchical Bayesian Modeling of Speaker Verification Scores
• SPRING: A fast stochastic proximal alternating method for non-smooth non-convex optimization
• A variable metric mini-batch proximal stochastic recursive gradient algorithm with diagonal Barzilai-Borwein stepsize
• Accelerating Convergence of Replica Exchange Stochastic Gradient MCMC via Variance Reduction
• A Statistician Teaches Deep Learning
• Competing with the Empirical Risk Minimizer in a Single Pass
• Stochastic Distributed Learning with Gradient Quantization and Variance Reduction
• A Free-Energy Principle for Representation Learning
• Post-Training at the Edge of Detectability: A Game-Theoretic Approach to Fine-Tuning
• Reclaiming the "frequentist" role of marginal likelihood in Bayesian belief revision
• Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview
• Stationary Behavior of Constant Stepsize SGD Type Algorithms: An Asymptotic Characterization
• The Minimax Complexity of Distributed Optimization
• Scalable Hyperparameter Optimization with Lazy Gaussian Processes
• Almost sure convergence and asymptotical normality of a generalization of Kesten's stochastic approximation algorithm for multidimensional case
• The Convergence of Stochastic Gradient Descent in Asynchronous Shared Memory
• Comparison-Based Algorithms for One-Dimensional Stochastic Convex Optimization
• Contrastive Mixture of Posteriors for Counterfactual Inference, Data Integration and Fairness
• Stochastic Gradient Hamiltonian Monte Carlo
• A Stochastic Quasi-Newton Method for Large-Scale Optimization
• Model-Free Risk-Sensitive Reinforcement Learning
• Discretize-Optimize vs. Optimize-Discretize for Time-Series Regression and Continuous Normalizing Flows
• FedBone: Towards Large-Scale Federated Multi-Task Learning
• Finite-Time Convergence Rates of Nonlinear Two-Time-Scale Stochastic Approximation under Markovian Noise
• Subgradient Methods for Nonsmooth Convex Functions with Adversarial Errors
• Bayesian Transfer Learning for High-Dimensional Linear Regression via Adaptive Shrinkage
• Reducing Noise in GAN Training with Variance Reduced Extragradient
• Characterizing signal propagation to close the performance gap in unnormalized ResNets
• On the Convergence of Adaptive Gradient Methods for Nonconvex Optimization
• Fully Implicit Online Learning
• Adaptive Gradient Descent for Optimal Control of Parabolic Equations with Random Parameters
• Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis
• Dynamic Network Embeddings for Network Evolution Analysis
• Monte Carlo Co-Ordinate Ascent Variational Inference
• High-Performance Large-Scale Image Recognition Without Normalization
• Sparsity-Probe: Analysis tool for Deep Learning Models
• Stochastic Gradient Descent for Relational Logistic Regression via Partial Network Crawls
• Truncated Stochastic Approximation with Moving Bounds: Convergence
• Temporal Difference Learning as Gradient Splitting
• Teaching Machine Learning to Software Engineers
• One-class Collaborative Filtering with Random Graphs: Annotated Version
• On the fast convergence of random perturbations of the gradient flow
• Large-scale empirical tuning and comparison of default optimizers for variational inference
• An efficient Averaged Stochastic Gauss-Newton algorithm for estimating parameters of non linear regressions models
• A Collective Learning Framework to Boost GNN Expressiveness
• Stochastic actor‐oriented models for network change
• A One-step Approach to Covariate Shift Adaptation
• Veridical Data Science
• Enhance Curvature Information by Structured Stochastic Quasi-Newton Methods
• Hamilton-Jacobi Deep Q-Learning for Deterministic Continuous-Time Systems with Lipschitz Continuous Controls
• Variational Policy Gradient Method for Reinforcement Learning with General Utilities
• Convergence in Models with Bounded Expected Relative Hazard Rates
• AdaX: Adaptive Gradient Descent with Exponential Long Term Memory
• Accelerated Almost-Sure Convergence Rates for Nonconvex Stochastic Gradient Descent using Stochastic Learning Rates
• KKT Conditions, First-Order and Second-Order Optimization, and Distributed Optimization: Tutorial and Survey
• Variational Calibration of Computer Models
• Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design
• A Variational Inequality Perspective on Generative Adversarial Networks
• Stochastic Variational Inference
• Finite-Sample Analysis of Nonlinear Stochastic Approximation with Applications in Reinforcement Learning
• The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure For Least Squares
• Decentralized Dynamic Discriminative Dictionary Learning
• U-CNNpred: A Universal CNN-based Predictor for Stock Markets
• Early Stopping without a Validation Set
• Riemannian stochastic quasi-Newton algorithm with variance reduction and its convergence analysis
• Convergence of a Relaxed Variable Splitting Coarse Gradient Descent Method for Learning Sparse Weight Binarized Activation Neural Networks
• Variational Inference: A Review for Statisticians
• Watch Where You Move: Region-aware Dynamic Aggregation and Excitation for Gait Recognition
• Primal Method for ERM with Flexible Mini-batching Schemes and Non-convex Losses
• Update estimation of diffusion parameter observed at high frequency
• Bayesian Projected Calibration of Computer Models
• An embarrassingly simple comparison of machine learning algorithms for indoor scene classification
• Stochastic Gradient Descent for Stochastic Doubly-Nonconvex Composite Optimization
• Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming
• BSFA: Leveraging the Subspace Dichotomy to Accelerate Neural Network Training
• Multi-Resolution Model Fusion for Accelerating the Convolutional Neural Network Training
• Training Across Reservoirs: Using Numerical Differentiation To Couple Trainable Networks With Black-Box Reservoirs
• Dynamically Weighted Momentum with Adaptive Step Sizes for Efficient Deep Network Training
• A Black Box Variational Inference Scheme for Inverse Problems with Demanding Physics-Based Models
• Maximum likelihood estimation of regularisation parameters in high-dimensional inverse problems: an empirical Bayesian approach. Part II: Theoretical Analysis
• Nonlinear forward-backward-half forward splitting with momentum for monotone inclusions
• Simplified Stochastic Feedforward Neural Networks
• ProxSARAH: An Efficient Algorithmic Framework for Stochastic Composite Nonconvex Optimization
• PredProp: Bidirectional Stochastic Optimization with Precision Weighted\n Predictive Coding
• Competitive Policy Optimization
• Optimal Control in Large Open Quantum Systems: The Case of Transmon Readout and Reset
• Advances in Variational Inference
• Dual Averaging is Surprisingly Effective for Deep Learning Optimization
• On the Saturation Phenomenon of Stochastic Gradient Descent for Linear Inverse Problems
• Connectome-Guided Automatic Learning Rates for Deep Networks
• Fast large-scale optimization by unifying stochastic gradient and quasi-Newton methods
• CURVETE: Curriculum Learning and Progressive Self-supervised Training for Medical Image Classification
• How Muon's Spectral Design Benefits Generalization: A Study on Imbalanced Data
• Optimal Matrix Momentum Stochastic Approximation and Applications to Q-learning
• Stopping Rules for Monte Carlo Methods: A Review
• A Minimal-Assumption Analysis of Q-Learning with Time-Varying Policies
• An Interval Hessian-based line-search method for unconstrained nonconvex optimization
• Distributed Stochastic Proximal Algorithm on Riemannian Submanifolds for Weakly-convex Functions
• An Improved Analysis of Stochastic Gradient Descent with Momentum
• Optimization in Theory and Practice
• Convergence Analysis of SGD under Expected Smoothness
• Reinforcement Learning and Consumption-Savings Behavior
• PSO-XAI: A PSO-Enhanced Explainable AI Framework for Reliable Breast Cancer Detection
• Fluctuation-dissipation relations for stochastic gradient descent
• Isotropic Noise in Stochastic and Quantum Convex Optimization
• From Optimization to Prediction: Transformer-Based Path-Flow Estimation to the Traffic Assignment Problem
• Statistical Inference for Linear Functionals of Online Least-squares SGD when t \gtrsim d^1+δ
• No Intelligence Without Statistics: The Invisible Backbone of Artificial Intelligence
• An Alternating Direction Method of Multipliers for Utility-based Shortfall Risk Portfolio Optimization
• A Unified Perspective on Optimization in Machine Learning and Neuroscience: From Gradient Descent to Neural Adaptation
• A Frequentist Statistical Introduction to Variational Inference, Autoencoders, and Diffusion Models
• A Compressive Sensing Inspired Monte-Carlo Method for Combinatorial Optimization
• Practical and Private (Deep) Learning without Sampling or Shuffling
• Relational Pooling for Graph Representations
• Continuous Q-Score Matching: Diffusion Guided Reinforcement Learning for Continuous-Time Control
• Bregman Stochastic Proximal Point Algorithm with Variance Reduction
• A termination criterion for stochastic gradient descent for binary classification
• Enhancing di-jet resonance searches via a final-state radiation jet tagging algorithm
• Ant colony optimization theory: A survey
• Accelerating Minibatch Stochastic Gradient Descent using Typicality Sampling
• Cumulative Prospect Theory Meets Reinforcement Learning: Prediction and Control
• LLM Priors for ERM over Programs
• Noise-Adaptive Layerwise Learning Rates: Accelerating Geometry-Aware Optimization for Deep Neural Network Training
• Hyper-Parameter Optimization: A Review of Algorithms and Applications
• Uncertainty Quantification for Online Learning and Stochastic Approximation via Hierarchical Incremental Gradient Descent
• The Implicit Regularization of Stochastic Gradient Flow for Least Squares
• A Stochastic Algorithm for Searching Saddle Points with Convergence Guarantee
• Randomness and Interpolation Improve Gradient Descent
• Stochastic gradient descent methods for estimation with large data sets
• Learning Latent Energy-Based Models via Interacting Particle Langevin Dynamics
• The Impact of Synthetic Data on Object Detection Model Performance: A Comparative Analysis with Real-World Data
• DRL: Discriminative Representation Learning with Parallel Adapters for Class Incremental Learning
• Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling
• Graph Pattern Mining and Learning through User-defined Relations (Extended Version)
• Accelerated stochastic first-order method for convex optimization under heavy-tailed noise
• The density of states from first principles
• Statistical Guarantees for High-Dimensional Stochastic Gradient Descent
• A Stochastic Differential Equation Framework for Multi-Objective LLM Interactions: Dynamical Systems Analysis with Code Generation Applications
• Mean-square and linear convergence of a stochastic proximal point algorithm in metric spaces of nonpositive curvature
• EA4LLM: A Gradient-Free Approach to Large Language Model Optimization via Evolutionary Algorithms
• Preconditioned Norms: A Unified Framework for Steepest Descent, Quasi-Newton and Adaptive Methods
• Sparsification as a Remedy for Staleness in Distributed Asynchronous SGD
• Distributed adaptive steplength stochastic approximation schemes for Cartesian stochastic variational inequality problems
• A Novel lightweight Convolutional Neural Network, ExquisiteNetV2
• Explicit Discovery of Nonlinear Symmetries from Dynamic Data
• Differentially Private Dropout
• Adaptive Path Sampling in Metastable Posterior Distributions
• Distributed Stochastic Approximation for Constrained and Unconstrained Optimization
• A Review of Learning with Deep Generative Models from Perspective of Graphical Modeling
• The Number of Steps Needed for Nonconvex Optimization of a Deep Learning\n Optimizer is a Rational Function of Batch Size
• Shapley Interpretation and Activation in Neural Networks
• Vertex-reinfoced random walk on Z visits finitely many states
• Instrumental Variable Value Iteration for Causal Offline Reinforcement Learning
• Adaptive Optimal Scaling of Metropolis-Hastings Algorithms Using the Robbins-Monro Process
• Mix- and MoE-DPO: A Variational Inference Approach to Direct Preference Optimization
• Ergodicity and error estimate of laws for a random splitting Langevin Monte Carlo
• A General Framework for Joint Multi-State Models
• Gradient Shaping Beyond Clipping: A Functional Perspective on Update Magnitude Control
• Local SGD Converges Fast and Communicates Little
• SGD without Replacement: Sharper Rates for General Smooth Convex Functions
• Dimensionality Reduction for Stationary Time Series via Stochastic Nonconvex Optimization
• Bayes Factor Tests for Group Differences in Ordinal and Binary Graphical Models
• Non-Asymptotic Analysis of Efficiency in Conformalized Regression
• Mechanism design and equilibrium analysis of smart contract mediated resource allocation
• SALAD: Self-Adaptive Link Adaptation
• A Probabilistic Basis for Low-Rank Matrix Learning
• Rethinking Langevin Thompson Sampling from A Stochastic Approximation Perspective
• Adaptive Memory Momentum via a Model-Based Framework for Deep Learning Optimization
• Stochastic Gradient Descent, Weighted Sampling, and the Randomized\n Kaczmarz algorithm
• A Statistical Framework for Low-bitwidth Training of Deep Neural Networks
• Thinking on the Fly: Test-Time Reasoning Enhancement via Latent Thought Policy Optimization
• ProxSTORM -- A Stochastic Trust-Region Algorithm for Nonsmooth Optimization
• SGD in the Large: Average-case Analysis, Asymptotics, and Stepsize Criticality
• Tricks from Deep Learning
• Asynchronous Federated Learning with Reduced Number of Rounds and with Differential Privacy from Less Aggregated Gaussian Noise
• Memory Determines Learning Direction: A Theory of Gradient-Based Optimization in State Space Models
• Extensions of Robbins-Siegmund Theorem with Applications in Reinforcement Learning
• Management Fads, Pedagogies and Soft Technologies
• Bundle Network: a Machine Learning-Based Bundle Method
• Stochastic variational inference for GARCH models
• Monotonic Transformation Invariant Multi-task Learning
• CE-FAM: Concept-Based Explanation via Fusion of Activation Maps
• An Investigation of Batch Normalization in Off-Policy Actor-Critic Algorithms
• Bridging Discrete and Continuous RL: Stable Deterministic Policy Gradient with Martingale Characterization
• An Improved Framework for Scaling Party Positions from Texts with Transformer
• Machine Reading Comprehension: a Literature Review
• Metric-based Regularization and Temporal Ensemble for Multi-task Learning using Heterogeneous Unsupervised Tasks
• GO Hessian for Expectation-Based Objectives
• AdaDelay: Delay Adaptive Distributed Stochastic Convex Optimization
• Continuous-Time Reinforcement Learning for Asset-Liability Management
• Convergence of online mirror descent
• InfiAgent: Self-Evolving Pyramid Agent Framework for Infinite Scenarios
• A regret minimization approach to fixed-point iterations
• Effective continuous equations for adaptive SGD: a stochastic analysis view
• Laplacian Smoothing Gradient Descent
• Stochastic Gradient MCMC Methods for Hidden Markov Models
• Shaping Initial State Prevents Modality Competition in Multi-modal Fusion: A Two-stage Scheduling Framework via Fast Partial Information Decomposition
• Quantum machine learning interatomic potential: Application of variational quantum algorithm
• Stochastic gradient descent with random learning rate
• Conservative set valued fields, automatic differentiation, stochastic gradient method and deep learning
• Training Continuously‐Coupled Reconfigurable Photonic Chips with Quantum Machine Learning
• An Improved Convergence Analysis of Stochastic Variance-Reduced Policy Gradient
• Adaptive Importance Sampling via Stochastic Convex Programming
• The Convergence Behavior of Adam under Heavy-Tailed Noise
• FORGE: Fused On-Register Gradient Elimination for Memory-Efficient LLM Training
• Quadruply Stochastic Gaussian Processes
• Reinforcement learning in convergently non-stationary environments: Feudal hierarchies and learned representations
• Harvest-or-Transmit Policy for Cognitive Radio Networks: A Learning Theoretic Approach
• Continuous Assortment Optimization with Logit Choice Probabilities under Incomplete Information
• Scalable Mean-Field Variational Inference via Preconditioned Primal-Dual Optimization
• Towards a Unified Architecture for in-RDBMS Analytics
• Stochastic Approximator of Motor Threshold (SAMT) for transcranial magnetic stimulation: Online software and its performance in clinical studies
• Variance Reduction for Evolution Strategies via Structured Control Variates
• Dual Control for Approximate Bayesian Reinforcement Learning
• Practical Quasi-Newton Methods for Training Deep Neural Networks
• Conditional Generative Modeling via Learning the Latent Space
• A Variant of Gradient Descent Algorithm Based on Gradient Averaging
• Asymptotic study of stochastic adaptive algorithm in non-convex landscape
• Characterization of Excess Risk for Locally Strongly Convex Population Risk
• Finite-temperature Yang-Mills theories with the density of states method: towards the continuum limit
• Integrating Stacked Intelligent Metasurfaces and Power Control for Dynamic Edge Inference via Over-The-Air Neural Networks
• Decentralized Control via Dynamic Stochastic Prices: The Independent System Operator Problem
• Differentiable Light Transport with Gaussian Surfels via Adapted Radiosity for Efficient Relighting and Geometry Reconstruction
• Antithetic variates in higher dimensions
• A consensus-based global optimization method for high dimensional machine learning problems
• Pathfinder: Parallel quasi-Newton variational inference
• Development of Deep Learning Optimizers: Approaches, Concepts, and Update Rules
• Faster On-Device Training Using New Federated Momentum Algorithm
• Zero-inflation in the Multivariate Poisson Lognormal Family
• Randomized Block Coordinate Descent for Online and Stochastic Optimization
• Graph Coloring for Multi-Task Learning
• The Root Finding Problem Revisited: Beyond the Robbins-Monro procedure
• Towards Robust Visual Continual Learning with Multi-Prototype Supervision
• Consciousness as a Functor
• VGG-TSwinformer: Transformer-based deep learning model for early Alzheimer’s disease prediction
• DIVEBATCH: Accelerating Model Training Through Gradient-Diversity Aware Batch Size Adaptation
• Bounding the expected run-time of nonconvex optimization with early stopping
• Almost sure convergence of dropout algorithms for neural networks
• Supervised and Unsupervised Deep Learning Applied to the Majority Vote Model
• Progressive Identification of True Labels for Partial-Label Learning
• Online Learning to Sample
• Dissecting Federated-Graph Aggregation under Domain Shift: Importance-Aware Aggregation via Empirical Analysis
• On Tackling High-Dimensional Nonconvex Stochastic Optimization via Stochastic First-Order Methods with Non-smooth Proximal Terms and Variance Reduction
• The No-U-Turn Sampler: Adaptively Setting Path Lengths in Hamiltonian Monte Carlo
• On the Convergence of SARAH and Beyond
• On the Convergence of Decentralized Adaptive Gradient Methods
• Accelerated Gradient Methods with Biased Gradient Estimates: Risk Sensitivity, High-Probability Guarantees, and Large Deviation Bounds
• Scaling Gaussian Processes with Derivative Information Using Variational Inference
• Extragradient method with variance reduction for stochastic variational inequalities
• Item Response Theory -- A Statistical Framework for Educational and Psychological Measurement
• A Unified Theory of SGD: Variance Reduction, Sampling, Quantization and\n Coordinate Descent
• Accelerated Gradient Methods for Nonconvex Nonlinear and Stochastic Programming
• On Empirical Comparisons of Optimizers for Deep Learning
• Learning Dependency-Based Compositional Semantics
• Artificial neural networks for neuroscientists: A primer
• A Multi-Batch L-BFGS Method for Machine Learning
• Revisiting the Polyak step size
• Optimal Subsampling for Data Streams with Measurement Constrained Categorical Responses
• Stochastic Neural Network with Kronecker Flow
• SVRG for Policy Evaluation with Fewer Gradient Evaluations
• Convergence Rate in Nonlinear Two-Time-Scale Stochastic Approximation with State (Time)-Dependence
• A Proximal Stochastic Gradient Method with Adaptive Step Size and Variance Reduction for Convex Composite Optimization
• Momentum-based variance-reduced proximal stochastic gradient method for composite nonconvex stochastic optimization
• Asymptotic distribution and convergence rates of stochastic algorithms\n for entropic optimal transportation between probability measures
• Heart Disease Prediction: A Comparative Study of Optimisers Performance in Deep Neural Networks
• Federated Optimization: Distributed Machine Learning for On-Device Intelligence
• Statistical Measures For Defining Curriculum Scoring Function
• Prescribe-then-Select: Adaptive Policy Selection for Contextual Stochastic Optimization
• SVN-ICP: Uncertainty Estimation of ICP-based LiDAR Odometry using Stein Variational Newton
• Online Robust and Adaptive Learning from Data Streams
• Stochastic Sign Descent Methods: New Algorithms and Better Theory
• Breaking the Conventional Forward-Backward Tie in Neural Networks: Activation Functions
• Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence
• Online Statistical Inference for Stochastic Optimization via Kiefer-Wolfowitz Methods
• History-Gradient Aided Batch Size Adaptation for Variance Reduced Algorithms
• Deep Learning for Markov Chains: Lyapunov Functions, Poisson's Equation, and Stationary Distributions
• An Interactive Framework for Finding the Optimal Trade-off in Differential Privacy
• A Study of Gradient Variance in Deep Learning
• Starting Small -- Learning with Adaptive Sample Sizes
• Stochasticity of Deterministic Gradient Descent: Large Learning Rate for Multiscale Objective Function
• Explicit Mean-Square Error Bounds for Monte-Carlo and Linear Stochastic Approximation
• Shuffling Heuristic in Variational Inequalities: Establishing New Convergence Guarantees
• Deep Gamblers: Learning to Abstain with Portfolio Theory
• An Overview of Lead and Accompaniment Separation in Music
• Learning Convex Optimization Control Policies
• EmbedOR: Provable Cluster-Preserving Visualizations with Curvature-Based Stochastic Neighbor Embeddings
• Network Implosion: Effective Model Compression for ResNets via Static Layer Pruning and Retraining
• Stochastic versus Deterministic in Stochastic Gradient Descent
• Learning Latent Space Energy-Based Prior Model
• GENO -- GENeric Optimization for Classical Machine Learning
• Understanding the Effects of Data Parallelism and Sparsity on Neural Network Training
• A Framework for Evaluating Gradient Leakage Attacks in Federated Learning
• Principled Design of Translation, Scale, and Rotation Invariant Variation Operators for Metaheuristics
• Online Sinkhorn: Optimal Transport distances from sample streams
• Convergence and Stability of the Stochastic Proximal Point Algorithm\n with Momentum
• GradES: Significantly Faster Training in Transformers with Gradient-Based Early Stopping
• Elastic Consistency: A General Consistency Model for Distributed Stochastic Gradient Descent
• Globally aware optimization with resurgence
• Proximal Backpropagation
• Distributed stochastic gradient tracking methods with momentum acceleration for non-convex optimization
• Convergence Rates of Stochastic Gradient Descent under Infinite Noise Variance
• Multiplicative noise and heavy tails in stochastic optimization
• A Contour Stochastic Gradient Langevin Dynamics Algorithm for Simulations of Multi-modal Distributions
• Accelerated, Optimal, and Parallel: Some Results on Model-Based Stochastic Optimization
• CNN with large memory layers
• Solutions for Mitotic Figure Detection and Atypical Classification in MIDOG 2025
• Extreme MRI: Large-Scale Volumetric Dynamic Imaging from Continuous Non-Gated Acquisitions
• Stochastic Online Feedback Optimization for Networks of Non-Compliant Agents
• Convergence of regularized agent-state-based Q-learning in POMDPs
• Calibrating generalized predictive distributions
• Revisit Stochastic Gradient Descent for Strongly Convex Objectives: Tight Uniform-in-Time Bounds
• A Twin Neural Model for Uplift
• The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient Descent
• Combined Stochastic and Robust Optimization for Electric Autonomous Mobility-on-Demand with Nested Benders Decomposition
• Federated Consistency- and Complementarity-aware Consensus-enhanced Recommendation
• A Model-agnostic Strategy to Mitigate Embedding Degradation in Personalized Federated Recommendation
• Backprop with Approximate Activations for Memory-efficient Network Training
• Renewable Quantile Regression with Heterogeneous Streaming Datasets
• Implicit particle filters for data assimilation
• GRADSTOP: Early Stopping of Gradient Descent via Posterior Sampling
• Learning with springs and sticks
• Dissipativity Theory for Accelerating Stochastic Variance Reduction: A Unified Analysis of SVRG and Katyusha Using Semidefinite Programs
• A Neural Network-Based On-device Learning Anomaly Detector for Edge Devices
• Variational Wasserstein Barycenters with c-Cyclical Monotonicity
• The Emergence of Compositional Languages for Numeric Concepts Through Iterated Learning in Neural Agents
• Optimal Auction Design for the Gradual Procurement of Strategic Service Provider Agents
• Universal Reinforcement Learning in Coalgebras: Asynchronous Stochastic Computation via Conduction
• Natural Compression for Distributed Deep Learning
• Information Directed Sampling for Sparse Linear Bandits
• Network formation in the interbank money market: An application of the actor-oriented model
• Explainable Learning Rate Regimes for Stochastic Optimization
• Beyond the Mean: Fisher-Orthogonal Projection for Natural Gradient Descent in Large Batch Training
• Learning dynamical systems with particle stochastic approximation EM
• Optimization Problems for Machine Learning: A Survey
• Stochastic Gradient Hamiltonian Monte Carlo with Variance Reduction for Bayesian Inference
• An Iterative Bayesian Robbins--Monro Sequence
• The Discrete Infinite Logistic Normal Distribution
• Enabling scalable stochastic gradient-based inference for Gaussian processes by employing the Unbiased LInear System SolvEr (ULISSE)
• Search of RRATs on declinations from +42^∘ to +55^∘ with a neural network
• Graph Neural Diffusion via Generalized Opinion Dynamics
• Contrastive Weight Regularization for Large Minibatch SGD
• SPAN: A Stochastic Projected Approximate Newton Method
• Belief Flows of Robust Online Learning
• A learning-driven automatic planning framework for proton PBS treatments of H&N cancers
• Hybrid Stochastic-Deterministic Minibatch Proximal Gradient: Less-Than-Single-Pass Optimization with Nearly Optimal Generalization
• Condition Number Analysis of Logistic Regression, and its Implications for Standard First-Order Solution Methods
• On the mean field limit of the Random Batch Method for interacting particle systems
• WeatherPrompt: Multi-modality Representation Learning for All-Weather Drone Visual Geo-Localization
• Natural Analysts in Adaptive Data Analysis
• How much progress have we made in neural network training? A New Evaluation Protocol for Benchmarking Optimizers
• Audio-Visual Speech Enhancement: Architectural Design and Deployment Strategies
• \(X\)-evolve: Solution space evolution powered by large language models
• Last-Iterate Complexity of SGD for Convex and Smooth Stochastic Problems
• Learn-and-Adapt Stochastic Dual Gradients for Network Resource Allocation
• Online Convex Optimization with Heavy Tails: Old Algorithms, New Regrets, and Applications
• Sample-Efficient Reinforcement Learning for Linearly-Parameterized MDPs with a Generative Model
• Training few-shot classification via the perspective of minibatch and pretraining
• Convergence of inertial dynamics and proximal algorithms governed by maximally monotone operators
• Federated and continual learning for classification tasks in a society of devices
• Adaptive Weight Decay for Deep Neural Networks
• High-Order Error Bounds for Markovian LSA with Richardson-Romberg Extrapolation
• Adaptive Batch Size and Learning Rate Scheduler for Stochastic Gradient Descent Based on Minimization of Stochastic First-order Oracle Complexity
• Generalized Inner Loop Meta-Learning
• ULU: A Unified Activation Function
• Stochastic Difference-of-Convex Algorithms for Solving nonconvex optimization problems
• Compressed Decentralized Momentum Stochastic Gradient Methods for Nonconvex Optimization
• No Masks Needed: Explainable AI for Deriving Segmentation from Classification
• Neural Network Training via Stochastic Alternating Minimization with Trainable Step Sizes
• CSG: A stochastic gradient method for a wide class of optimization problems appearing in a machine learning or data-driven context
• QuantNet: Learning to Quantize by Learning within Fully Differentiable Framework
• Accelerating SGDM via Learning Rate and Batch Size Schedules: A Lyapunov-Based Analysis
• Breaking the Top-K Barrier: Advancing Top-K Ranking Metrics Optimization in Recommender Systems
• SGD for Structured Nonconvex Functions: Learning Rates, Minibatching and Interpolation
• Computationally efficient Gauss-Newton reinforcement learning for model predictive control
• SGD momentum optimizer with step estimation by online parabola model
• Server Averaging for Federated Learning
• Stochastic Reweighted Gradient Descent
• Soft Separation and Distillation: Toward Global Uniformity in Federated Unsupervised Learning
• Training Deep Neural Networks by optimizing over nonlocal paths in hyperparameter space
• Personalized Transformer for Explainable Recommendation
• Efficient variational inference for generalized linear mixed models with large datasets
• Neighbor-Sampling Based Momentum Stochastic Methods for Training Graph Neural Networks
• Advancing Welding Defect Detection in Maritime Operations via Adapt-WeldNet and Defect Detection Interpretability Analysis
• EMA Without the Lag: Bias-Corrected Iterate Averaging Schemes
• Stochastic variance reduced multiplicative update for nonnegative matrix factorization
• FADO: A Deterministic Detection/Learning Algorithm
• Popov Mirror-Prox Method for Variational Inequalities
• Formal Bayesian Transfer Learning via the Total Risk Prior
• Investigating the Invertibility of Multimodal Latent Spaces: Limitations of Optimization-Based Methods
• Personalized Dynamic Treatment Regimes in Continuous Time: A Bayesian Approach for Optimizing Clinical Decisions with Timing
• Quantifying the mini-batching error in Bayesian inference for Adaptive Langevin dynamics
• Do We Need Zero Training Loss After Achieving Zero Training Error?
• Explaining Natural Language Processing Classifiers with Occlusion and Language Modeling
• An em algorithm for quantum Boltzmann machines
• Quantum optical shallow networks
• Stochastic gradient with least-squares control variates
• Stochastic Block BFGS: Squeezing More Curvature out of Data
• Stochastic Quantum Hamiltonian Descent
• Stochastic gradient variational Bayes for gamma approximating distributions
• Computational Advantages of Multi-Grade Deep Learning: Convergence Analysis and Performance Insights
• Layerwise Optimization by Gradient Decomposition for Continual Learning
• Learning Latent Graph Geometry via Fixed-Point Schrödinger-Type Activation: A Theoretical Study
• Dimer-Enhanced Optimization: A First-Order Approach to Escaping Saddle Points in Neural Network Training
• Reverse engineering learned optimizers reveals known and novel mechanisms
• Unit Tests for Stochastic Optimization
• Efficiency of the Wang-Landau algorithm: a simple test case
• A Langevinized Ensemble Kalman Filter for Large-Scale Static and Dynamic Learning
• QLSD: Quantised Langevin stochastic dynamics for Bayesian federated learning
• Stochastic Optimization for Performative Prediction
• Stochastic Search with an Observable State Variable
• Non-Gaussianity of Stochastic Gradient Noise
• A Dimension-free Algorithm for Contextual Continuum-armed Bandits
• Probabilistic Line Searches for Stochastic Optimization
• Stochastic gradient-free descents
• Data Sampling Strategies in Stochastic Algorithms for Empirical Risk Minimization
• Hybrid tensor network and neural network quantum states for quantum chemistry
• The Price equation reveals a universal force-metric-bias law of algorithmic learning and natural selection
• Adaptively Preconditioned Stochastic Gradient Langevin Dynamics
• Fishers for Free? Approximating the Fisher Information Matrix by Recycling the Squared Gradient Accumulator
• SGD with Coordinate Sampling: Theory and Practice
• Selection dynamics for deep neural networks
• Mini-batch stochastic Nesterov's smoothing method for constrained convex stochastic composite optimization
• Multiple Kernel Learning from Noisy Labels by Stochastic Programming
• A Semismooth Newton Method for Support Vector Classification and Regression
• Accelerate Distributed Stochastic Descent for Nonconvex Optimization with Momentum
• Almost sure convergence rates for Stochastic Gradient Descent and Stochastic Heavy Ball
• Stochastic gradient algorithms from ODE splitting perspective
• Traversing the noise of dynamic mini-batch sub-sampled loss functions: A visual guide
• Unified Optimal Analysis of the (Stochastic) Gradient Method
• Reducing the variance in online optimization by transporting past gradients
• A Unified Stochastic Gradient Approach to Designing Bayesian-Optimal Experiments
• L-SVRG and L-Katyusha with Arbitrary Sampling
• Quadrature Compound: An approximating family of distributions
• BODAME: Bilevel Optimization for Defense Against Model Extraction
• The Power of Factorial Powers: New Parameter settings for (Stochastic)\n Optimization
• Contributions to Large Scale Bayesian Inference and Adversarial Machine Learning
• An Elementary Proof that Q-learning Converges Almost Surely
• Statistical Inference in High-dimensional Generalized Linear Models with Streaming Data
• Improving SAGA via a Probabilistic Interpolation with Gradient Descent
• ADASECANT: Robust Adaptive Secant Method for Stochastic Gradient
• Coupling Adaptive Batch Sizes with Learning Rates
• Elephant random walks with multiple extractions and general reinforcement functions
• A Cross Entropy based Stochastic Approximation Algorithm for Reinforcement Learning with Linear Function Approximation
• Self-Supervised Sketch-to-Image Synthesis
• Mixing ADAM and SGD: a Combined Optimization Method
• Statistical and Algorithmic Foundations of Reinforcement Learning
• Reliable uncertainty estimate for antibiotic resistance classification with Stochastic Gradient Langevin Dynamics
• A distributed adaptive steplength stochastic approximation method for monotone stochastic Nash Games
• Zap Q-Learning With Nonlinear Function Approximation
• Sequential Design for Computerized Adaptive Testing that Allows for Response Revision
• The stochastic multi-gradient algorithm for multi-objective optimization and its application to supervised machine learning
• Optimal Routing for Delay-Sensitive Traffic in Overlay Networks
• Semi-Supervised Classification and Segmentation on High Resolution Aerial Images
• Uniform Sampling over Episode Difficulty
• Asynchronous stochastic convex optimization
• Step-DAD: Semi-Amortized Policy-Based Bayesian Experimental Design
• OptTyper: Probabilistic Type Inference by Optimising Logical and Natural Constraints
• Online First-Order Framework for Robust Convex Optimization
• Federated Accelerated Stochastic Gradient Descent
• ShadowSync: Performing Synchronization in the Background for Highly Scalable Distributed Training
• Why Does Multi-Epoch Training Help?
• Adjoint-based trailing edge shape optimization of a transonic turbine vane using large eddy simulations
• Melodic Phrase Segmentation By Deep Neural Networks
• Stochastic Collapsed Variational Bayesian Inference for Latent Dirichlet Allocation
• Consensus-based Distributed Quantile Estimation in Sensor Networks
• DNT: a Deeply Normalized Transformer that can be trained by Momentum SGD
• Doubly-stochastic mining for heterogeneous retrieval
• A Partitioned Sparse Variational Gaussian Process for Fast, Distributed Spatial Modeling
• NPO: Learning Alignment and Meta-Alignment through Structured Human Feedback
• Modern Bayesian Experimental Design
• Signed Distance Function Computation from an Implicit Surface
• Decentralized Markov Chain Gradient Descent
• RS-TinyNet: Stage-wise Feature Fusion Network for Detecting Tiny Objects in Remote Sensing Images
• Neural Architecture Search with Mixed Bio-inspired Learning Rules
• Stochastic Weakly Convex Optimization Under Heavy-Tailed Noises
• Communication-Efficient Distributed Dual Coordinate Ascent
• Convergence of Batch Asynchronous Stochastic Approximation With Applications to Reinforcement Learning
• Stochastic Approximate Gradient Descent via the Langevin Algorithm
• Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity
• Stochastic Recursive Gradient Algorithm for Nonconvex Optimization
• Optimization Methods for Large-Scale Machine Learning
• Blockwise Adaptivity: Faster Training and Better Generalization in Deep Learning
• Cutting Slack: Quantum Optimization with Slack-Free Methods for Combinatorial Benchmarks
• Spatial Frequency Modulation for Semantic Segmentation
• Convergence Rate of Generalized Nash Equilibrium Learning in Strongly Monotone Games with Linear Constraints
• Beyond Ground States: Physics-Inspired Optimization of Excited States of Classical Hamiltonians
• LoRA meets Riemannion: Muon Optimizer for Parametrization-independent Low-Rank Adapters
• Inference by Stochastic Optimization: A Free-Lunch Bootstrap
• Recursive Bound-Constrained AdaGrad with Applications to Multilevel and Domain Decomposition Minimization
• Incremental Adaptation of NMT for Professional Post-editors: A User Study
• Neumann Optimizer: A Practical Optimization Algorithm for Deep Neural Networks
• SMG: A Shuffling Gradient-Based Method with Momentum
• Learning values across many orders of magnitude
• Natural Language Understanding with Distributed Representation
• Parameter estimation using simultaneous perturbation stochastic approximation
• Learning Generative Prior with Latent Space Sparsity Constraints
• A Latent Morphology Model for Open-Vocabulary Neural Machine Translation
• Measure Transport with Kernel Stein Discrepancy
• Two-Scale Stochastic Control for Multipoint Communication Systems with Renewables
• Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information
• A Dynamic Sampling Adaptive-SGD Method for Machine Learning
• ProcData: An R Package for Process Data Analysis
• Fast Incremental Expectation Maximization for finite-sum optimization: nonasymptotic convergence
• A Stochastic Penalty Model for Convex and Nonconvex Optimization with Big Constraints
• TauRieL: Targeting Traveling Salesman Problem with a deep reinforcement learning inspired architecture
• NysAct: A Scalable Preconditioned Gradient Descent using Nystrom Approximation
• Adaptive Bayesian Sampling with Monte Carlo EM
• Towards Practical Adam: Non-Convexity, Convergence Theory, and Mini-Batch Acceleration
• Sketch and Project: Randomized Iterative Methods for Linear Systems and Inverting Matrices
• A Stochastic Gradient Method with an Exponential Convergence Rate for Finite Training Sets
• EAdam Optimizer: How ε Impact Adam
• Converting the Point of View of Messages Spoken to Virtual Assistants
• FrostNet: Towards Quantization-Aware Network Architecture Search
• Risk-Averse Approximate Dynamic Programming with Quantile-Based Risk Measures
• Asynchronous Decentralized Stochastic Optimization in Heterogeneous Networks
• Stochastic Newton and Cubic Newton Methods with Simple Local Linear-Quadratic Rates
• LyAm: Robust Non-Convex Optimization for Stable Learning in Noisy Environments
• Non-smooth stochastic gradient descent using smoothing functions
• A Stochastic Gradient Descent Theorem and the Back-Propagation Algorithm
• Uncertainty Quantification for Gradient and Accelerated Gradient Descent Methods on Strongly Convex Functions
• SGD Converges to Global Minimum in Deep Learning via Star-convex Path
• A Multi-Step Richardson-Romberg Extrapolation Method For Stochastic Approximation
• Asynchronous Optimization Methods for Efficient Training of Deep Neural Networks with Guarantees
• Kernel-based Approximate Bayesian Inference for Exponential Family Random Graph Models
• Fast and Accurate Stellar Mass Predictions from Broad-Band Magnitudes with a Simple Neural Network: Application to Simulated Star-Forming Galaxies
• Stochastic Variational Inference for Hidden Markov Models
• Computational Aspects for Interface Identification Problems with Stochastic Modelling
• On Smoothing, Regularization and Averaging in Stochastic Approximation Methods for Stochastic Variational Inequalities
• On Biased Stochastic Gradient Estimation
• Zorse: Optimizing LLM Training Efficiency on Heterogeneous GPU Clusters
• Convergence Rates and Decoupling in Linear Stochastic Approximation Algorithms
• Generic Behaviour of Strongly Reinforced Polya Urns : Convergence and Stability
• A modified tamed scheme for stochastic differential equations with superlinear drifts
• Optimal High-probability Convergence of Nonlinear SGD under Heavy-tailed Noise via Symmetrization
• Stochastic Approximation with Block Coordinate Optimal Stepsizes
• Finite-Time Analysis of Stochastic Gradient Descent under Markov Randomness
• Robust, Accurate Stochastic Optimization for Variational Inference
• Gaussian variational approximation with a factor covariance structure
• NOWPAC: A provably convergent derivative-free nonlinear optimizer with path-augmented constraints
• Convergence Rate for the Last Iterate of Stochastic Gradient Descent Schemes
• Adaptive collaboration for online personalized distributed learning with heterogeneous clients
• Stochastic TCO minimization for Video Transmission over IP Networks
• Concerning the differentiability of the energy function in vector quantization algorithms
• Accelerated Large Batch Optimization of BERT Pretraining in 54 minutes
• SoftSignSGD(S3): An Enhanced Optimizer for Practical DNN Training and Loss Spikes Minimization Beyond Adam
• Non-Asymptotic Analysis of Online Local Private Learning with SGD
• Approximately Exact Line Search
• Online Robust Subspace Tracking from Partial Information
• Free energy computations by minimization of Kullback-Leibler divergence: an efficient adaptive biasing potential method for sparse representations
• Bidirectional compression in heterogeneous settings for distributed or federated learning with partial participation: tight convergence guarantees
• Online Learning as Stochastic Approximation of Regularization Paths
• Adaptivity via a Parallel Architecture for Stochastic Gradient Methods
• Efficient Federated Learning with Timely Update Dissemination
• Ampere: Communication-Efficient and High-Accuracy Split Federated Learning
• Computer-aided analyses of stochastic first-order methods, via interpolation conditions for stochastic optimization
• Necessary condition for sparse optimal control problem with intermediate constraints
• Visual Identification of Individual Holstein-Friesian Cattle via Deep Metric Learning
• Machine Learning's Dropout Training is Distributionally Robust Optimal
• Kalman Filter Aided Federated Koopman Learning
• Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal
• Cyclic Differentiable Architecture Search
• Temporal Conformal Prediction (TCP): A Distribution-Free Statistical and Machine Learning Framework for Adaptive Risk Forecasting
• Mini-batch Stochastic Approximation Methods for Nonconvex Stochastic Composite Optimization
• Adversarial Data Augmentation for Single Domain Generalization via Lyapunov Exponent-Guided Optimization
• Deep Lyapunov Function: Automatic Stability Analysis for Dynamical Systems
• On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data
• Low-Rank Factorization of Determinantal Point Processes for Recommendation
• Dynamical Isometry: The Missing Ingredient for Neural Network Pruning
• Local SGD: Unified Theory and New Efficient Methods
• Distributed Second Order Methods with Fast Rates and Compressed Communication
• Privacy for Free: Posterior Sampling and Stochastic Gradient Monte Carlo
• Predicting the mechanical response of oligocrystals with deep learning
• Addressing Algorithmic Bottlenecks in Elastic Machine Learning with Chicle
• Statistical Inference for Stochastic Gradient Descent: Beyond Finite Variance
• Identifying and Analyzing Sepsis States: A Retrospective Study on Patients with Sepsis in ICUs
• Robust Brain Tumor Segmentation with Incomplete MRI Modalities Using Hölder Divergence and Mutual Information-Enhanced Knowledge Transfer
• Training Neural Networks Using Features Replay
• AuON: A Linear-time Alternative to Semi-Orthogonal Momentum Updates
• Finite-Time Analysis of Asynchronous Stochastic Approximation and Q-Learning
• Data-Driven Exploration for a Class of Continuous-Time Indefinite Linear--Quadratic Reinforcement Learning Problems
• Harnessing the Power of Reinforcement Learning for Adaptive MCMC
• An Adaptive State Aggregation Algorithm for Markov Decision Processes
• Large-scale Neural Network Quantum States for ab initio Quantum Chemistry Simulations on Fugaku
• Both Asymptotic and Non-Asymptotic Convergence of Quasi-Hyperbolic Momentum using Increasing Batch Size
• Graph Drawing by Stochastic Gradient Descent
• Computing a human-like reaction time metric from stable recurrent vision models
• Two Spelling Normalization Approaches Based on Large Language Models
• Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods
• DeepWukong
• Hierarchical Variational Models
• A High Probability Analysis of Adaptive SGD with Momentum
• WavShape: Information-Theoretic Speech Representation Learning for Fair and Privacy-Aware Audio Processing
• Learning Threshold-Type Investment Strategies with Stochastic Gradient Method
• Exact Adversarial Attack to Image Captioning via Structured Output Learning with Latent Variables
• Trade-offs of Local SGD at Scale: An Empirical Study
• Learning Curves for SGD on Structured Features
• Generalized Adaptation for Few-Shot Learning
• Generalized Polya urns via stochastic approximation
• Asynchronous adaptive networks
• A Spatio-Temporal Point Process for Fine-Grained Modeling of Reading Behavior
• Optimization-Induced Dynamics of Lipschitz Continuity in Neural Networks
• Recursive Optimization of Convex Risk Measures: Mean-Semideviation Models
• Variational Variance: Simple, Reliable, Calibrated Heteroscedastic Noise Variance Parameterization
• Hindsight-Guided Momentum (HGM) Optimizer: An Approach to Adaptive Learning Rate
• Stochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization
• Noise-induced degeneration in online learning
• PDFNet: Pointwise Dense Flow Network for Urban-Scene Segmentation
• A Tutorial on Bayesian Optimization
• Noise-Informed Diffusion-Generated Image Detection with Anomaly Attention
• On the Complexity of Minimizing Convex Finite Sums Without Using the Indices of the Individual Functions
• Riemannian Stochastic Hybrid Gradient Algorithm for Nonconvex Optimization
• Non-asymptotic Analysis of Biased Stochastic Approximation Scheme
• A Novel Indicator for Quantifying and Minimizing Information Utility Loss of Robot Teams
• A Study of Hybrid and Evolutionary Metaheuristics for Single Hidden Layer Feedforward Neural Network Architecture
• Don't Use Large Mini-Batches, Use Local SGD
• A Stochastic Proximal Gradient Framework for Decentralized Non-Convex Composite Optimization: Topology-Independent Sample Complexity and Communication Efficiency
• Gravilon: Applications of a New Gradient Descent Method to Machine Learning
• Monte Carlo methods: Application to hydrogen gas and hard spheres
• A Stochastic Successive Minimization Method for Nonsmooth Nonconvex Optimization with Applications to Transceiver Design in Wireless Communication Networks
• Global Convergence and Stability of Stochastic Gradient Descent
• Scalable and Efficient Comparison-based Search without Features
• Stochastic first-order methods: non-asymptotic and computer-aided analyses via potential functions
• A Sharp Estimate on the Transient Time of Distributed Stochastic Gradient Descent
• Automated proof synthesis for propositional logic with deep neural networks
• Glocal Smoothness: Line search and adaptive step sizes can help in theory too!
• An approximate Riemann solver approach in Physics-Informed Neural Networks for hyperbolic conservation laws
• Differential Privacy in Machine Learning: From Symbolic AI to LLMs
• A stochastic second-order generalized estimating equations approach for estimating intraclass correlation coefficient in the presence of informative missing data
• Towards Undistillable Models by Minimizing Conditional Mutual Information
• Stochastic Heavy Ball
• RollingQ: Reviving the Cooperation Dynamics in Multimodal Transformer
• Simpler, Faster, Stronger: Breaking The log-K Curse On Contrastive Learners With FlatNCE
• Uncertainty-Aware Strategies: A Model-Agnostic Framework for Robust Financial Optimization through Subsampling
• Mean Field Games without Rational Expectations
• Convergence of Momentum-Based Optimization Algorithms with Time-Varying Parameters
• Dynamic Stochastic Approximation for Multi-stage Stochastic Optimization
• Stagewise Enlargement of Batch Size for SGD-based Learning
• ASMOP: Additional sampling stochastic trust region method for multi-objective problems
• Stacey: Promoting Stochastic Steepest Descent via Accelerated ℓ_p-Smooth Nonconvex Optimization
• Path Integral Optimiser: Global Optimisation via Neural Schrödinger-Föllmer Diffusion
• Direct Fisher Score Estimation for Likelihood Maximization
• Parsimonious Inference
• The limits of min-max optimization algorithms: convergence to spurious non-critical sets
• ACFNet: Attentional Class Feature Network for Semantic Segmentation
• Speed learning on the fly
• A Machine-Learning Method for Time-Dependent Wave Equations over Unbounded Domains
• Rapid training of Hamiltonian graph networks using random features
• Boosting Variational Inference
• Quantum sequel of neural network training
• Do optimization methods in deep learning applications matter?
• KOALA++: Efficient Kalman-Based Optimization with Gradient-Covariance Products
• Boulevard: Regularized Stochastic Gradient Boosted Trees and Their Limiting Distribution
• Weighted Aggregating Stochastic Gradient Descent for Parallel Deep Learning
• Knowledge Distillation as Semiparametric Inference
• Continuous-time Models for Stochastic Optimization Algorithms
• Online Matching in Sparse Random Graphs: Non-Asymptotic Performances of\n Greedy Algorithm
• Uniform-in-Time Weak Error Analysis for Stochastic Gradient Descent Algorithms via Diffusion Approximation
• Using Social Network Information in Bayesian Truth Discovery
• On Stochastic Gradient and Subgradient Methods with Adaptive Steplength\n Sequences
• New First-Order Algorithms for Stochastic Variational Inequalities
• A Distributed Hierarchical SGD Algorithm with Sparse Global Reduction
• No More Pesky Learning Rates
• How Data Augmentation affects Optimization for Linear Regression
• Online Asynchronous Distributed Regression
• Variance Regularization for Accelerating Stochastic Optimization
• On the Discrepancy Principle for Stochastic Gradient Descent
• Regret in Online Combinatorial Optimization
• Nonparametric Learning Algorithms for Joint Pricing and Inventory Control with Lost Sales and Censored Demand
• Parameter-free Stochastic Optimization of Variationally Coherent Functions
• Recent Advances in Deep Learning for Object Detection
• Revisiting the Characteristics of Stochastic Gradient Noise and Dynamics
• Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms
• Direct Acceleration of SAGA using Sampled Negative Momentum
• Hogwild! over Distributed Local Data Sets with Linearly Increasing Mini-Batch Sizes
• Simultaneous Model Selection and Optimization through Parameter-free Stochastic Learning
• Fast Fourier Transform-Based Spectral and Temporal Gradient Filtering for Differential Privacy
• When Does Stochastic Gradient Algorithm Work Well?
• Dynamic Collaborative Filtering with Compound Poisson Factorization
• Gradient-only line searches to automatically determine learning rates for a variety of stochastic training algorithms
• Structured Actor-Critic for Managing Public Health Points-of-Dispensing
• Coulomb GANs: Provably Optimal Nash Equilibria via Potential Fields
• Stochastic Functional Gradient Path Planning in Occupancy Maps
• Stochastic Gradient Descent on a Tree: an Adaptive and Robust Approach to Stochastic Convex Optimization
• Dense Prediction with Attentive Feature Aggregation
• A Complete Recipe for Stochastic Gradient MCMC
• Bayesian Inference Forgetting
• Latent Guided Sampling for Combinatorial Optimization
• Distributed Forward-Backward algorithms for stochastic generalized Nash equilibrium seeking
• Accelerated Stochastic Quasi-Newton Optimization on Riemann Manifolds
• How neural networks find generalizable solutions: Self-tuned annealing in deep learning
• Asymptotics of SGD in Sequence-Single Index Models and Single-Layer Attention Networks
• Multilevel Stochastic Gradient Descent for Optimal Control Under Uncertainty
• Variational Inference via χ-Upper Bound Minimization
• A Tree-guided CNN for image super-resolution
• Tensor Normal Training for Deep Learning Models
• Quantitative LLM Judges
• Learning to Optimize in Swarms
• Overfitting or Underfitting? Understand Robustness Drop in Adversarial Training
• Self-supervised Latent Space Optimization with Nebula Variational Coding
• Local Expectation Gradients for Doubly Stochastic Variational Inference
• Taming LLMs by Scaling Learning Rates with Gradient Grouping
• A Closer Look at Deep Policy Gradients
• Are All Languages Equally Hard to Language-Model?
• FedQuad: Adaptive Layer-wise LoRA Deployment and Activation Quantization for Federated Fine-Tuning
• Energy Time Ptychography for one-dimensional phase retrieval
• Semi-Implicit Back Propagation
• Sketchy Empirical Natural Gradient Methods for Deep Learning
• Wasserstein Distance Maximizing Intrinsic Control
• On Variance Reduction in Stochastic Gradient Descent and its Asynchronous Variants
• Optimization of neural networks via finite-value quantum fluctuations
• Stochastic Block Mirror Descent Methods for Nonsmooth and Stochastic Optimization
• Hyper-Sphere Quantization: Communication-Efficient SGD for Federated Learning
• Stochastic Belief Propagation: A Low-Complexity Alternative to the Sum-Product Algorithm
• Throughput Optimal Decentralized Scheduling of Multi-Hop Networks with End-to-End Deadline Constraints: II Wireless Networks with Interference
• A Probabilistically Motivated Learning Rate Adaptation for Stochastic Optimization
• On the convergence of mirror descent beyond stochastic convex programming
• DSAGL: Dual-Stream Attention-Guided Learning for Weakly Supervised Whole Slide Image Classification
• Towards Open-Text Semantic Parsing via Multi-Task Learning of Structured Embeddings
• Training Dynamic Exponential Family Models with Causal and Lateral Dependencies for Generalized Neuromorphic Computing
• Random directions stochastic approximation with deterministic perturbations
• Stochastic Variational Inference for Bayesian Sparse Gaussian Process Regression
• Algorithms for Kullback-Leibler Approximation of Probability Measures in\n Infinite Dimensions
• Smoothed Gradients for Stochastic Variational Inference
• Screening for Sparse Online Learning
• Taming Transformer Without Using Learning Rate Warmup
• Stochastic Approximation, Cooperative Dynamics and Supermodular Games
• An efficient algorithm for numerical computations of continuous densities of states
• New Convergence Aspects of Stochastic Gradient Algorithms
• Convergence of Clipped-SGD for Convex (L₀,L₁)-Smooth Optimization with Heavy-Tailed Noise
• Stochastic Euler Schemes and Dissipative Evolutions in the Space of Probability Measures
• Sharpness-Aware Minimization with Z-Score Gradient Filtering
• Connecting randomized iterative methods with Krylov subspaces
• AutoSGD: Automatic Learning Rate Selection for Stochastic Gradient Descent
• Multi-objective Large Language Model Alignment with Hierarchical Experts
• On The Convergence of Euler Discretization of Finite-Time Convergent Gradient Flows
• A General-Purpose Theorem for High-Probability Bounds of Stochastic Approximation with Polyak Averaging
• Nearly Dimension-Independent Convergence of Mean-Field Black-Box Variational Inference
• Finite-Sample Analysis of Stochastic Approximation Using Smooth Convex Envelopes
• Weight-Preserving Simulated Tempering
• ViewCraft3D: High-Fidelity and View-Consistent 3D Vector Graphics Synthesis
• Investigating Alternatives to the Root Mean Square for Adaptive Gradient Methods
• Meta-Learning Bidirectional Update Rules
• Distributed Learning and its Application for Time-Series Prediction
• Connecting Independently Trained Modes via Layer-Wise Connectivity
• On the Robustness of Average Losses for Partial-Label Learning
• Fast Variational Inference for Bayesian Factor Analysis in Single and Multi-Study Settings
• Oracle inequalities for computationally adaptive model selection
• A Simple Algorithm for Scalable Monte Carlo Inference
• A Bayesian Perspective of Convolutional Neural Networks through a Deconvolutional Generative Model
• Designing Pin-pression Gripper and Learning its Dexterous Grasping with Online In-hand Adjustment
• A Natural Actor-Critic Algorithm with Downside Risk Constraints
• Do Large Language Models (Really) Need Statistical Foundations?
• k-SVRG: Variance Reduction for Large Scale Optimization
• Joint-stochastic-approximation Random Fields with Application to Semi-supervised Learning
• Joint-stochastic-approximation Autoencoders with Application to Semi-supervised Learning
• Convergence, Sticking and Escape: Stochastic Dynamics Near Critical Points in SGD
• A variational approach to stochastic minimization of convex functionals
• Gradient-only line searches: An Alternative to Probabilistic Line Searches
• On Linear Stochastic Approximation: Fine-grained Polyak-Ruppert and Non-Asymptotic Concentration
• An iterative regularized mirror descent method for ill-posed nondifferentiable stochastic optimization
• A New Approach for Optimizing Highly Nonlinear Problems Based on the Observer Effect Concept
• Stochastic Gradient Descent for Linear Systems with Missing Data
• Two-Player Games for Efficient Non-Convex Constrained Optimization
• Dynamic Dual Buffer with Divide-and-Conquer Strategy for Online Continual Learning
• Riemannian stochastic recursive momentum method for non-convex optimization
• New Tight Bounds for SGD without Variance Assumption: A Computer-Aided Lyapunov Analysis
• Asymptotic normality of randomly truncated stochastic algorithms
• NeuroTrails: Training with Dynamic Sparse Heads as the Key to Effective Ensembling
• Stochastic Approximation versus Sample Average Approximation for population Wasserstein barycenters
• Ergodic Mirror Descent
• Language modeling with Neural trans-dimensional random fields
• EMRA-proxy: Enhancing Multi-Class Region Semantic Segmentation in Remote Sensing Images with Attention Proxy
• Why Diffusion Models Don't Memorize: The Role of Implicit Dynamical Regularization in Training
• Multi-cut stochastic approximation methods for solving stochastic convex composite optimization
• NPTC-net: Narrow-Band Parallel Transport Convolutional Neural Network on Point Clouds
• Fast Stochastic Methods for Nonsmooth Nonconvex Optimization
• Online Statistical Inference of Constrained Stochastic Optimization via Random Scaling
• Statistical Inference for Online Algorithms
• Risk-Averse Reinforcement Learning with Itakura-Saito Loss
• Estimation and uncertainty quantification for the output from quantum simulators
• A Two-Stage Data Selection Framework for Data-Efficient Model Training on Edge Devices
• On the Almost Sure Convergence of Stochastic Gradient Descent in Non-Convex Problems
• Adaptive Stochastic Optimization
• Stochastic optimization for numerical evaluation of imprecise probabilities
• Safe Learning under Uncertain Objectives and Constraints
• Convergence of Adam in Deep ReLU Networks via Directional Complexity and Kakeya Bounds
• Statistical Adaptive Stochastic Gradient Methods
• VAMO: Efficient Zeroth-Order Variance Reduction for SGD with Faster Convergence
• Robustness, Privacy, and Generalization of Adversarial Training
• A theoretical and empirical study of new adaptive algorithms with additional momentum steps and shifted updates for stochastic non-convex optimization
• ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains
• Pathwise Derivatives Beyond the Reparameterization Trick
• KO: Kinetics-inspired Neural Optimizer with PDE Simulation Approaches
• CBA: Contextual Quality Adaptation for Adaptive Bitrate Video Streaming (Extended Version)
• An Adaptive Sample Size Trust-Region Method for Finite-Sum Minimization
• A Selective Overview of Deep Learning
• Characterizing nonatomic admissions markets
• Fine-tuning Quantized Neural Networks with Zeroth-order Optimization
• Smoothed SGD for quantiles: Bahadur representation and Gaussian approximation
• Surrogate Optimization of Deep Neural Networks for Groundwater Predictions
• PydMobileNet: Improved Version of MobileNets with Pyramid Depthwise Separable Convolution
• Bandwidth-based Step-Sizes for Non-Convex Stochastic Optimization
• Bias-Variance Tradeoff in a Sliding Window Implementation of the Stochastic Gradient Algorithm
• Stochastic Approximation Hamiltonian Monte Carlo
• A Stochastic Quasi-Newton Method for Large-Scale Nonconvex Optimization with Applications
• The Stochastic Multi-Proximal Method for Nonsmooth Optimization
• The Curious Case of the Default Settings: Evaluating Default Performance of Variational Inference Software
• Never Skip a Batch: Dense Learning of Temporal GNNs via Adaptive Pseudo-Supervision
• CROSSBOW: Scaling Deep Learning with Small Batch Sizes on Multi-GPU Servers
• DeepOBS: A Deep Learning Optimizer Benchmark Suite
• An Exploratory Analysis of the Latent Structure of Process Data via Action Sequence Autoencoder
• Modified swarm-based metaheuristics enhance Gradient Descent initialization performance: Application for EEG spatial filtering
• Keep the Gradients Flowing: Using Gradient Flow to Study Sparse Network Optimization
• Revisiting Stochastic Approximation and Stochastic Gradient Descent
• A Unifying Probabilistic View of Associative Learning
• VIP - Variational Inversion Package with example implementations of Bayesian tomographic imaging
• Tight Dimension Independent Lower Bound on the Expected Convergence Rate for Diminishing Step Sizes in SGD
• On Stochastic Variance Reduced Gradient Method for Semidefinite Optimization
• Joint Status Sampling and Updating for Minimizing Age of Information in the Internet of Things
• Convergence Analysis of the Last Iterate in Distributed Stochastic Gradient Descent with Momentum
• Controlling the Flow: Stability and Convergence for Stochastic Gradient Descent with Decaying Regularization
• Percolation Threshold Results on \Erdos-\Renyi Graphs: an Empirical Process Approach
• A 140 line MATLAB code for topology optimization problems with probabilistic parameters
• Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search
• Incorporating brain-inspired mechanisms for multimodal learning in artificial intelligence
• DeepSeqCoco: A Robust Mobile Friendly Deep Learning Model for Detection of Diseases in Cocos nucifera
• An Exponential Averaging Process with Strong Convergence Properties
• Stochastic Item Descent Method for Large Scale Equal Circle Packing Problem
• Spike-timing-dependent Hebbian learning as noisy gradient descent
• SAD Neural Networks: Divergent Gradient Flows and Asymptotic Optimality via o-minimal Structures
• The stochastic Auxiliary Problem Principle in Banach spaces: measurability and convergence
• Evaluating Visual Properties via Robust HodgeRank
• Phases of learning dynamics in artificial neural networks: with or without mislabeled data
• A Latent Variational Framework for Stochastic Optimization
• Distributed Training of Deep Neural Network Acoustic Models for Automatic Speech Recognition
• Distributed Stochastic Algorithms for High-rate Streaming Principal Component Analysis
• Gravity Optimizer: a Kinematic Approach on Optimization in Deep Learning
• Generative Text Modeling through Short Run Inference
• Online differentially private inference in stochastic gradient descent
• Consistency and fluctuations for stochastic gradient Langevin dynamics
• A random batch Ewald method for particle systems with Coulomb interactions
• Fast-Mixing Markov Chains without Gradients
• Sharp Gaussian approximations for Decentralized Federated Learning
• Machine Learning on Volatile Instances
• Orthogonal-Padé Activation Functions: Trainable Activation functions for smooth and faster convergence in deep networks
• Sharp Analysis for Nonconvex SGD Escaping from Saddle Points
• Bant: Byzantine Antidote via Trial Function and Trust Scores
• Learning-based Bias Correction for Ultra-wideband Localization of Resource-constrained Mobile Robots
• Stochastic ADMM with batch size adaptation for nonconvex nonsmooth optimization
• Stochastic Cubic Regularization for Fast Nonconvex Optimization
• A Simple Stochastic Variance Reduced Algorithm with Fast Convergence Rates
• A Second look at Exponential and Cosine Step Sizes: Simplicity, Adaptivity, and Performance
• Convergence in quadratic mean of averaged stochastic gradient algorithms\n without strong convexity nor bounded gradient
• Stochastic DCA for minimizing a large sum of DC functions with application to Multi-class Logistic Regression
• FedADP: Unified Model Aggregation for Federated Learning with Heterogeneous Model Architectures
• Towards Probabilistic Verification of Machine Unlearning
• KML: Using Machine Learning to Improve Storage Systems
• Age of Processing: Age-driven Status Sampling and Processing Offloading for Edge Computing-enabled Real-time IoT Applications
• Generative Modeling by Inclusive Neural Random Fields with Applications in Image Generation and Anomaly Detection
• Two-stage Linear Decision Rules for Multi-stage Stochastic Programming
• Extended Fiducial Inference for Individual Treatment Effects via Deep Neural Networks
• Variational Inference: A Review for Statisticians
• Advances in Asynchronous Parallel and Distributed Optimization
• Memory-Efficient LLM Training by Various-Grained Low-Rank Projection of Gradients
• DRSLF: Double Regularized Second-Order Low-Rank Representation for Web Service QoS Prediction
• A Stochastic forward-backward splitting method for solving monotone inclusions in Hilbert spaces
• FTNILO: Explicit Multivariate Function Inversion, Optimization and Counting, Cryptography Weakness and Riemann Hypothesis Solution Equation with Tensor Networks
• Stochastic optimization methods for the simultaneous control of\n parameter-dependent systems
• Time Adaptive Reinforcement Learning
• A Provably Convergent Plug-and-Play Framework for Stochastic Bilevel Optimization
• Consciousness in AI: Logic, Proof, and Experimental Evidence of Recursive Identity Formation
• Analysis of nonsmooth stochastic approximation: the differential inclusion approach
• Balanced Alignment for Face Recognition: A Joint Learning Approach
• Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization
• Distributed Derivative-free Learning Method for Stochastic Optimization over a Network with Sparse Activity
• Trust-Region Algorithms for Training Responses: Machine Learning Methods\n Using Indefinite Hessian Approximations
• Particle-based Generalised Stochastic Optimisation
• signProx: One-Bit Proximal Algorithm for Nonconvex Stochastic Optimization
• A Unifying Framework for Variance Reduction Algorithms for Finding Zeroes of Monotone Operators
• Optimal Primal-Dual Methods for a Class of Saddle Point Problems
• Gonogo: An R Implementation of Test Methods to Perform, Analyze and Simulate Sensitivity Experiments
• Differentiable Visual Computing
• Efficient and Robust Algorithms for Adversarial Linear Contextual Bandits
• Optimum Experimental Designs
• Demystifying Parallel and Distributed Deep Learning
• Accelerating Mini-batch SARAH by Step Size Rules
• Computing hitting times via fluid approximation: application to the coupon collector problem
• Convex Optimization: Algorithms and Complexity
• Explicit Regularization of Stochastic Gradient Methods through Duality
• Randomized Block Subgradient Methods for Convex Nonsmooth and Stochastic Optimization
• Reinforced stochastic gradient descent for deep neural network learning
• RBUE: A ReLU-Based Uncertainty Estimation Method of Deep Neural Networks
• Quantile estimation with adaptive importance sampling
• Smoothed Hinge Loss and ℓ¹ Support Vector Machines
• Variance Reduction for Distributed Stochastic Gradient Descent
• MTL2L: A Context Aware Neural Optimiser
• Learning Retrospective Knowledge with Reverse Reinforcement Learning
• Finding best approximation pairs for two intersections of closed convex sets
• Stochastic Annealing
• Hessian based analysis of SGD for Deep Nets: Dynamics and Generalization
• Patterns, predictions, and actions: A story about machine learning
• From Persistent Homology to Reinforcement Learning with Applications for Retail Banking
• WNGrad: Learn the Learning Rate in Gradient Descent
• Fast Transient Simulation of High-Speed Channels Using Recurrent Neural Network
• Non-Gaussian processes and neural networks at finite widths
• Convergence Rates of Accelerated Markov Gradient Descent with Applications in Reinforcement Learning
• Second-order Information in First-order Optimization Methods
• Conjugate-gradient-based Adam for stochastic optimization and its application to deep learning
• Latent Variable Session-Based Recommendation
• Non-asymptotic analysis of online noisy stochastic gradient descent
• Some aspects of the sequential design of experiments
• Meta knowledge assisted Evolutionary Neural Architecture Search
• Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation
• Contagion Networks: Evaluator Preference Propagation in Multi-Agent LLM Systems
• Second-Order Path Kernel Interpolation Formulas in Machine Learning
• Fast Compute for ML Optimization
• Improving the stability of the covariance-controlled adaptive Langevin thermostat for large-scale Bayesian sampling
• IPAS: An Adaptive Sample Size Method for Weighted Finite Sum Problems with Linear Equality Constraints
• O(1/k) Finite-Time Bound for Non-Linear Two-Time-Scale Stochastic Approximation
• HyperController: A Hyperparameter Controller for Fast and Stable Training of Reinforcement Learning Neural Networks
• Natural Language Embeddings of Synthesis and Testing conditions Enhance Glass Dissolution Prediction
• Gradient Descent's Last Iterate is Often (slightly) Suboptimal
• Revisiting Transformers through the Lens of Low Entropy and Dynamic Sparsity
• A Langevin sampling algorithm inspired by the Adam optimizer
• CAMeL: Cross-modality Adaptive Meta-Learning for Text-based Person Retrieval
• Extrapolation Guarantees for Perturbation Modeling Under the Additive Latent Shift Assumption
• Linear Least-Squares Algorithms for Temporal Difference Learning
• Noise-Driven Exploration and Transient Freezing Select Flat Minima in Stochastic Gradient Descent
• On Nonconvex Optimization for Machine Learning: Gradients, Stochasticity, and Saddle Points
• Online Pairwise Learning Algorithms with Kernels
• Stochastic Saddle Avoidance Beyond Unit Excitation and Smoothness: A Pathwise Lyapunov-Perron Framework
• On the Convergence of Consensus Algorithms with Markovian Noise and Gradient Bias
• Stochastic Gradient Descent with Polyak's Learning Rate
• Finite Time Analysis of Linear Two-timescale Stochastic Approximation with Markovian Noise
• An Inverse Source Problem for Semilinear Stochastic Hyperbolic Equations
• Backtracking Gradient Descent Method and Some Applications in Large Scale Optimisation. Part 2: Algorithms and Experiments
• Stochastic gradient descent, weighted sampling, and the randomized Kaczmarz algorithm
• Silenzio: Secure Non-Interactive Outsourced MLP Training
• Improving Deep Knowledge Tracing via Gated Architectures and Adaptive Optimization
• Distributed SAGA: Maintaining linear convergence rate with limited communication
• Optimal minimization of an unknown function in a nonparametric multivariate regression model thanks to a dimension reduction approach
• A stochastic alternating direction method of multipliers for non-smooth and non-convex optimization
• Active Learning Via Sequential Design and Uncertainty Sampling
• On PyTorch Implementation of Density Estimators for von Mises-Fisher and Its Mixture
• Моментные оценки для стохастической аппроксимации
• Deep convolutional neural networks for uncertainty propagation in random fields
• Randomised Splitting Methods and Stochastic Gradient Descent
• Provable Failure of Language Models in Learning Majority Boolean Logic via Gradient Descent
• Memory Limited, Streaming PCA
• Stochastic proximal gradient methods for nonconvex problems in Hilbert spaces
• Dynamic sampling schemes for optimal noise learning under multiple\n nonsmooth constraints
• Strong error analysis for the stochastic momentum optimizer
• Langevin Markov Chain Monte Carlo with stochastic gradients
• Covariant Gradient Descent
• Fast X-Ray CT Image Reconstruction Using a Linearized Augmented Lagrangian Method With Ordered Subsets
• DS-MLR: Exploiting Double Separability for Scaling up Distributed\n Multinomial Logistic Regression
• FrogDogNet: Fourier frequency Retained visual prompt Output Guidance for Domain Generalization of CLIP in Remote Sensing
• On an inferential model construction using generalized associations
• Efficient neural-network based variational Monte Carlo scheme for direct optimization of excited energy states in frustrated quantum systems
• GRADIENT-BASED STOCHASTIC OPTIMIZATION METHODS IN BAYESIAN EXPERIMENTAL DESIGN
• Bayesian sample size calculations for external validation studies of risk prediction models
• Towards Understanding Acceleration Tradeoff between Momentum and Asynchrony in Nonconvex Stochastic Optimization
• Stochastic Damped L-BFGS with Controlled Norm of the Hessian Approximation
• THE SELF-ORGANIZED MULTI-LATTICE MONTE CARLO SIMULATION
• A neural network-based framework for financial model calibration
• A framework for adaptive Monte Carlo procedures
• A Diffusion Approximation Theory of Momentum SGD in Nonconvex Optimization
• Stochastic Optimization with Optimal Importance Sampling
• An XAI-based Analysis of Shortcut Learning in Neural Networks
• Stochastic approximation with random step sizes and urn models with random replacement matrices having finite mean
• Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQL
• Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARL
• Geometric Learning Dynamics
• Learning Supervised Topic Models for Classification and Regression from Crowds
• EXPLICIT HESTON SOLUTIONS AND STOCHASTIC APPROXIMATION FOR PATH-DEPENDENT OPTION PRICING
• Convergence of distributed asynchronous learning vector quantization algorithms
• Ensemble Kalman inversion: a derivative-free technique for machine learning tasks
• Constrained clustering and Kohonen Self-Organizing Maps
• PyFRep: Shape Modeling with Differentiable Function Representation
• Rethinking Client-oriented Federated Graph Learning
• Computing Equilibria in Stochastic Nonconvex and Non-monotone Games via Gradient-Response Schemes
• Sequential Scenario-Specific Meta Learner for Online Recommendation
• A Common Derivation for Markov Chain Monte Carlo Algorithms with Tractable and Intractable Targets
• A Robbins–Monro procedure for estimation in semiparametric regression models
• Randomized Kaczmarz with Averaging
• Block layer decomposition schemes for training deep neural networks
• Variational Quantum Monte Carlo Simulations with Tensor-Network States
• Momentum Schemes with Stochastic Variance Reduction for Nonconvex\n Composite Optimization
• On the Convergence of Reinforcement Learning with Monte Carlo Exploring Starts
• VecHGrad for Solving Accurately Complex Tensor Decomposition
• Rethinking Curriculum Learning with Incremental Labels and Adaptive Compensation
• Ouroboros: On Accelerating Training of Transformer-Based Language Models
• G_mst:An Unbiased Stratified Statistic and a Fast Gradient Optimization Algorithm Based on It
• FPGA: Fast Patch-Free Global Learning Framework for Fully End-to-End Hyperspectral Image Classification
• Dimension-free convergence rates for gradient Langevin dynamics in RKHS
• Self-Tuned Mirror Descent Schemes for Smooth and Nonsmooth High-Dimensional Stochastic Optimization
• Large-Batch Training for LSTM and Beyond
• Multi-level stochastic approximation algorithms
• An overview of SPSA: recent development and applications
• Heterogeneous Multilayer Generalized Operational Perceptron
• SGD-Net: Efficient Model-Based Deep Learning With Theoretical Guarantees
• Deep convolutions for in-depth automated rock typing
• A Parallel Decomposition Method for Nonconvex Stochastic Multi-Agent Optimization Problems
• Distributed Variational Bayesian Algorithms Over Sensor Networks
• A Stochastic Subgradient Method for Distributionally Robust Non-Convex Learning
• Fast or Slow: An Autonomous Speed Control Approach for UAV-assisted IoT Data Collection Networks
• Gradient-Free Sequential Bayesian Experimental Design via Interacting Particle Systems
• Scaling transition from momentum stochastic gradient descent to plain stochastic gradient descent
• Stochastic Gradient Methods with Block Diagonal Matrix Adaptation
• Second-order Optimization of Gaussian Splats with Importance Sampling
• Faster State Preparation across Quantum Phase Transition Assisted by Reinforcement Learning
• Stochastic Gradient Descent in Non-Convex Problems: Asymptotic Convergence with Relaxed Step-Size via Stopping Time Methods
• Leave-One-Out Stable Conformal Prediction
• A proximal subgradient method for nonconvex stochastic optimization under the Kurdyka-Łojasiewicz condition
• Multi-resolution Score-Based Variational Graphical Diffusion for Causal Disaster System Modeling and Inference
• Parameter-Efficient Semantic Augmentation for Enhancing Open-Vocabulary Object Detection
• Understanding the theoretical properties of projected Bellman equation, linear Q-learning, and approximate value iteration
• Molecular Learning Dynamics
• MiMu: Mitigating Multiple Shortcut Learning Behavior of Transformers
• A Tale of Two Learning Algorithms: Multiple Stream Random Walk and Asynchronous Gossip
• Towards Weaker Variance Assumptions for Stochastic Optimization
• DUE: A Deep Learning Framework and Library for Modeling Unknown Equations
• Fairness is in the details: Face Dataset Auditing
• A Piecewise Lyapunov Analysis of Sub-quadratic SGD: Applications to Robust and Quantile Regression
• Deriving the Gradients of Some Popular Optimal Transport Algorithms
• In almost all shallow analytic neural network optimization landscapes, efficient minimizers have strongly convex neighborhoods
• Representation Meets Optimization: Training PINNs and PIKANs for Gray-Box Discovery in Systems Pharmacology
• Adam revisited: a weighted past gradients perspective
• Gaze-Guided Learning: Avoiding Shortcut Bias in Visual Classification
• Contrastive Decoupled Representation Learning and Regularization for Speech-Preserving Facial Expression Manipulation
• Weighted Approximate Quantum Natural Gradient for Variational Quantum Eigensolver
• Stochastic Variational Inference with Tuneable Stochastic Annealing
• A Geometric Framework for Stochastic Iterations
• Backtracking line search [wikipedia]
• Event-driven contrastive divergence for spiking neuromorphic systems. [europepmc]
• A Unifying Probabilistic View of Associative Learning. [europepmc]
• Midbrain Synchrony to Envelope Structure Supports Behavioral Sensitivity to Single-Formant Vowel-Like Sounds in Noise. [europepmc]
• Cerebellar learning using perturbations. [europepmc]
• RPITER: A Hierarchical Deep Learning Framework for ncRNA⁻Protein Interaction Prediction. [europepmc]
• Deeper Profiles and Cascaded Recurrent and Convolutional Neural Networks for state-of-the-art Protein Secondary Structure Prediction. [europepmc]
• DeepPoseKit, a software toolkit for fast and robust animal pose estimation using deep learning. [europepmc]
• Knowing What You Know in Brain Segmentation Using Bayesian Deep Neural Networks. [europepmc]
• Classification of brain tumor isocitrate dehydrogenase status using MRI and deep learning. [europepmc]
• LRRpredictor-A New LRR Motif Detection Method for Irregular Motifs of Plant NLR Proteins Using an Ensemble of Classifiers. [europepmc]
• Modern Soft-Sensing Modeling Methods for Fermentation Processes. [europepmc]
• A deep learning based framework for the registration of three dimensional multi-modal medical images of the head. [europepmc]
• Practices and Applications of Convolutional Neural Network-Based Computer Vision Systems in Animal Farming: A Review. [europepmc]
• MSU-Net: Multi-Scale U-Net for 2D Medical Image Segmentation. [europepmc]
• EDLMFC: an ensemble deep learning framework with multi-scale features combination for ncRNA-protein interaction prediction. [europepmc]
• Using smart speakers to contactlessly monitor heart rhythms. [europepmc]
• Classification of Diffuse Glioma Subtype from Clinical-Grade Pathological Images Using Deep Transfer Learning. [europepmc]
• AI in drug development: a multidisciplinary perspective. [europepmc]
• Advancements in Oncology with Artificial Intelligence-A Review Article. [europepmc]
• Pre-trained deep learning models for brain MRI image classification. [europepmc]
• Automated Classification of Brain Tumors from Magnetic Resonance Imaging Using Deep Learning. [europepmc]
• Compact optical convolution processing unit based on multimode interference. [europepmc]
• Developmental changes in exploration resemble stochastic optimization. [europepmc]
• Three novel methods for determining motor threshold with transcranial magnetic stimulation outperform conventional procedures. [europepmc]
• Brain Tumor Classification from MRI Using Image Enhancement and Convolutional Neural Network Techniques. [europepmc]

Related

• Stochastic Estimation of the Maximum of a Regression Function
• Evaluating Expectations of Functionals of Brownian Motions: a Multilevel Idea
• Asymptotic Variance in the Central Limit Theorem for Multilevel Markovian Stochastic Approximation
• Multi-level stochastic approximation algorithms
• General multilevel adaptations for stochastic approximation algorithms