Convergence of a Block Coordinate Descent Method for Nondifferentiable Minimization

2001/06/01 by P. Tseng · 95 citations
Engineering · Mathematics · Computer Science · #Sparse and Compressive Sensing Techniques #Advanced Optimization Algorithms Research #Stochastic Gradient Optimization Techniques

paper · doi:10.1023/a:1017501703105

Cited by

• Proximal alternating linearized minimization for nonconvex and nonsmooth problems
• ℓ₀ Minimization for wavelet frame based image restoration
• Euclidean Distance Geometry and Applications
• Optimization by Direct Search: New Perspectives on Some Classical and Modern Methods
• Topology-aware block coordinate descent for qubit frequency allocation of superconducting quantum processors
• Detecting Approximate Reflection Symmetry in a Point Set using\n Optimization on Manifold
• Truth Discovery in Sequence Labels from Crowds
• Improved Search Strategies with Application to Estimating Facial Blendshape Parameters
• On the Finite Time Convergence of Cyclic Coordinate Descent Methods
• Proceedings of the second "international Traveling Workshop on Interactions between Sparse models and Technology" (iTWIST'14)
• Localized Multiple Kernel Learning---A Convex Approach
• Group-sparse SVD Models and Their Applications in Biological Data
• Dynamic Average Diffusion with randomized Coordinate Updates
• PruneX: A Hierarchical Communication-Efficient System for Distributed CNN Training with Structured Pruning
• Second Degree Model for Multi-Compression and Recovery of Distributed\n Signals
• Convergent and efficient iteratively regularized contrast source inversion-type methods for inverse medium scattering problems
• Heuristics for Efficient Sparse Blind Source Separation
• Simultaneous Heterogeneity and Reduced-rank Learning for Multivariate Response Regression
• Improved Estimation of High-dimensional Ising Models
• Exact block-wise optimization in group lasso and sparse group lasso for\n linear regression
• ParaBlock: Communication-Computation Parallel Block Coordinate Federated Learning for Large Language Models
• Structured Matching via Cost-Regularized Unbalanced Optimal Transport
• Foundations of Artificial Intelligence Frameworks: Notion and Limits of AGI
• Movable Intelligent Surface-Enabled Wireless Communications: Static Phase Shifts with Mechanical Reconfigurability
• Disciplined Multi-Convex Programming
• Collapsing Categories for Regression with Mixed Predictors
• A flexible block-coordinate forward-backward algorithm for non-smooth and non-convex optimization
• Neural Blind Deconvolution Using Deep Priors
• A Generic First-Order Algorithmic Framework for Bi-Level Programming Beyond Lower-Level Singleton
• A Unified Algorithmic Framework for Block-Structured Optimization Involving Big Data: With applications in machine learning and signal processing
• Differentially Private Coordinate Descent for Composite Empirical Risk Minimization
• A provably convergent alternating minimization method for mean field\n inference
• A recursive divide-and-conquer approach for sparse principal component analysis
• Distributed Optimization via Adaptive Regularization for Large Problems\n with Separable Constraints
• Automatic Debiased Machine Learning of Causal and Structural Effects
• An efficient parallel block coordinate descent algorithm for large-scale precision matrix estimation using graphics processing units
• CellMCD+: An improved outlier-resistant cellwise minimum covariance determinant method
• Resource Allocation for IRS-assisted Full-Duplex Cognitive Radio Systems
• KKT Conditions, First-Order and Second-Order Optimization, and Distributed Optimization: Tutorial and Survey
• Distributed Sparse Linear Regression
• Decentralized Dynamic Discriminative Dictionary Learning
• Extended ADMM and BCD for Nonseparable Convex Minimization Models with Quadratic Coupling Terms: Convergence Analysis and Insights
• Faster Unbalanced Optimal Transport: Translation invariant Sinkhorn and 1-D Frank-Wolfe
• MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling
• Adaptive Sensing Performance Design for Enhancing Secure Communication in Networked ISAC Systems
• Block Coordinate Descent for Neural Networks Provably Finds Global Minima
• Cell-Free Millimeter-Wave Massive MIMO Systems with Limited Fronthaul\n Capacity
• Hierarchical Overlapping Group Lasso for GMANOVA Model
• Lasso Meets Horseshoe: A Survey
• Composite Lp-quantile regression, near quantile regression and the oracle model selection theory
• Communication-Efficient Algorithms For Distributed Optimization
• Multiple Operator-valued Kernel Learning
• Joint Transceiver Design for Wireless Sensor Networks through Block Coordinate Descent Optimization
• Near Optimal Sketching of Low-Rank Tensor Regression
• Robustness of Covariance Estimators with Application in Activity Detection
• The Sliding Frank-Wolfe Algorithm and its Application to\n Super-Resolution Microscopy
• Proximal Alternating Minimization and Projection Methods for Nonconvex Problems: An Approach Based on the Kurdyka-Łojasiewicz Inequality
• Non-Vacuous Generalization Bounds: Can Rescaling Invariances Help?
• Position-Blind Ptychography: Viability of image reconstruction via data-driven variational inference
• Residual-Driven Lifting Identification for Nonlinear-Manifold Reduced-Order Models of Parametrized Linear PDEs
• From safe screening rules to working sets for faster Lasso-type solvers
• Group descent algorithms for nonconvex penalized linear and logistic regression models with grouped predictors
• Joint User Scheduling and Beam Selection Optimization for Beam-Based Massive MIMO Downlinks
• Joint Base Station Clustering and Beamformer Design for Partial Coordinated Transmission in Heterogenous Networks
• Dual Extrapolation for Sparse Generalized Linear Models
• Structured Regularization for conditional Gaussian Graphical Models
• A coordinate-wise optimization algorithm for the Fused Lasso
• Randomized Block Coordinate Descent for Online and Stochastic Optimization
• DiEP: Adaptive Mixture-of-Experts Compression through Differentiable Expert Pruning
• Modelling peaks over thresholds in panel data: a two-level grouped panel generalized Pareto regression
• Signed Graph Learning with Hidden Nodes
• Data-driven nonlinear aerodynamics models with certifiably optimal boundedness properties
• Automated Hierarchical Graph Construction for Multi-source Electronic Health Records
• Joint Spatial and Spectral Hybrid Precoding for Multi-User MIMO-OFDM Systems
• From Fourier to Koopman: Spectral Methods for Long-term Time Series Prediction
• Asynchronous Variance-reduced Block Schemes for Composite Nonconvex Stochastic Optimization: Block-specific Steplengths and Adapted Batch-sizes
• Integrated Principal Components Analysis
• Gene-Environment Interaction: A Variable Selection Perspective
• On global convergence of alternating least squares for tensor approximation
• Iteration Complexity of Randomized Block-Coordinate Descent Methods for\n Minimizing a Composite Function
• Regularized Tensor Factorizations and Higher-Order Principal Components Analysis
• Block Distributed Majorize-Minimize Memory Gradient Algorithm and its\n application to 3D image restoration
• Conic Formulations of Transport Metrics for Unbalanced Measure Networks and Hypernetworks
• Energy-Efficient UAV Backscatter Communication with Joint Trajectory Design and Resource Optimization
• Randomized Fast Subspace Descent Methods
• Learning Gaussian DAGs from Network Data
• Neural Network Training via Stochastic Alternating Minimization with Trainable Step Sizes
• Stabilizing Deep Tomographic Reconstruction
• Formal Bayesian Transfer Learning via the Total Risk Prior
• Model compression as constrained optimization, with application to neural nets. Part V: combining compressions
• Framework for Multi-task Multiple Kernel Learning and Applications in Genome Analysis
• Relative Interior Rule in Block-Coordinate Minimization
• Graphical Elastic Net and Target Matrices: Fast Algorithms and Software\n for Sparse Precision Matrix Estimation
• A Statistically Identifiable Model for Tensor-Valued Gaussian Random\n Variables
• Wasserstein regularization for sparse multi-task regression