Dylan J. Foster
- Spectrally-normalized margin bounds for neural networks
2017/06/26 by Peter L. Bartlett, Bartlett, Peter, Dylan J. Foster +3 · 83 citations
Computer Science · #Neural Networks and Applications #Machine Learning and ELM #Face and Expression Recognition
- Lower Bounds for Non-Convex Stochastic Optimization
2019/12/05 by Yossi Arjevani, Arjevani, Yossi, Yair Carmon +9 · 27 citations
Computer Science · Mathematics · Engineering · #Stochastic Gradient Optimization Techniques #Markov Chains and Monte Carlo Methods #Sparse and Compressive Sensing Techniques
- The Statistical Complexity of Interactive Decision Making
2021/12/27 by Dylan J. Foster, Sham M. Kakade, Foster, Dylan J. +5 · 1 voice · 13 citations
Computer Science · Decision Sciences · Mathematics · #Advanced Bandit Algorithms Research #Data Stream Mining Techniques #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Algorithms #Optimization and Control (math.OC) #Statistics Theory (math.ST) #cs.LG #math.OC #math.ST #stat.ML
- Self-Improvement in Language Models: The Sharpening Mechanism
2024/12/02 by Audrey Huang, Adam Block, Huang, Audrey +13 · 2 voices · 24 citations
Computer Science · #Natural Language Processing Techniques #Topic Modeling #cs.AI #cs.CL #cs.LG #stat.ML
- Can large language models explore in-context?
2024/03/22 by Akshay Krishnamurthy, Krishnamurthy, Akshay, Keegan Harris +7 · 2 voices · 15 citations
Computer Science · #Natural Language Processing Techniques
- Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF
2024/05/31 by Tengyang Xie, Dylan J. Foster, Xie, Tengyang +10 · 1 voice · 19 citations
Computer Science · Mathematics · #Advanced Data Compression Techniques #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Data Management and Algorithms #FOS: Computer and information sciences #Face and Expression Recognition #Machine Learning (cs.LG) #Machine Learning (stat.ML) #cs.AI #cs.CL #cs.LG #stat.ML
- Independent Policy Gradient Methods for Competitive Reinforcement\n Learning
2021/01/11 by Constantinos Daskalakis, Dylan J. Foster, Daskalakis, Constantinos +3 · 11 citations
Computer Science · Decision Sciences · Physics and Astronomy · #Advanced Bandit Algorithms Research #Advanced Thermodynamics and Statistical Mechanics #FOS: Computer and information sciences #Machine Learning (cs.LG) #Reinforcement Learning in Robotics
- Adaptive Online Learning
2015/08/21 by Dylan J. Foster, Alexander Rakhlin, Foster, Dylan J. +3 · 7 citations
Decision Sciences · Computer Science · #Advanced Bandit Algorithms Research #Machine Learning and Algorithms #Stochastic Gradient Optimization Techniques
- Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning
2024/07/20 by Dylan J. Foster, Adam Block, Foster, Dylan J. +3 · 18 citations
Computer Science · Social Sciences · #Reinforcement Learning in Robotics #Language and cultural evolution
- Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment
2025/03/27 by Audrey Huang, Adam Block, Huang, Audrey +9 · 2 voices · 20 citations
#cs.AI #cs.LG #stat.ML
- Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective
2020/10/07 by Dylan J. Foster, Foster, Dylan J., Alexander Rakhlin +5 · 10 citations
Decision Sciences · Computer Science · #Advanced Bandit Algorithms Research #Reinforcement Learning in Robotics #Data Stream Mining Techniques
- Foundations of Reinforcement Learning and Interactive Decision Making
2023/12/27 by Dylan J. Foster, Alexander Rakhlin, Foster, Dylan J. +1 · 2 voices · 6 citations
Computer Science · Engineering · Mathematics · #Advanced Control Systems Optimization #COVID-19 epidemiological studies #Data Stream Mining Techniques #cs.LG #math.OC #math.ST #stat.ML
- Uniform Convergence of Gradients for Non-Convex Learning and Optimization
2018/10/25 by Dylan J. Foster, Foster, Dylan J., Ayush Sekhari +3 · 5 citations
Computer Science · Engineering · #Stochastic Gradient Optimization Techniques #Sparse and Compressive Sensing Techniques #Domain Adaptation and Few-Shot Learning
- Adapting to Misspecification in Contextual Bandits
2021/07/12 by Dylan J. Foster, Foster, Dylan J., Claudio Gentile +5 · 7 citations
Computer Science · Decision Sciences · #Advanced Bandit Algorithms Research #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Algorithms
- Naive Exploration is Optimal for Online LQR
2020/01/27 by Max Simchowitz, Dylan J. Foster, Simchowitz, Max +1 · 11 citations
Decision Sciences · Physics and Astronomy · Engineering · #Advanced Bandit Algorithms Research #Model Reduction and Neural Networks #Advanced Adaptive Filtering Techniques
- Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization
2024/07/18 by Audrey Huang, Huang, Audrey, Wenhao Zhan +11 · 1 voice · 9 citations
Computer Science · Engineering · #Advanced Multi-Objective Optimization Algorithms #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural Networks and Applications #Topology Optimization in Engineering #cs.AI #cs.CL #cs.LG
- Guaranteed Discovery of Control-Endogenous Latent States with Multi-Step Inverse Models
2022/07/17 by Alex Lamb, Lamb, Alex, Riashat Islam +17 · 5 citations
Computer Science · #Time Series Analysis and Forecasting #Reinforcement Learning in Robotics #AI-based Problem Solving and Planning
- Logarithmic Regret for Adversarial Online Control
2020/02/29 by Dylan J. Foster, Foster, Dylan J., Max Simchowitz +1 · 8 citations
Decision Sciences · Computer Science · #Advanced Bandit Algorithms Research #Reinforcement Learning in Robotics #Gaussian Processes and Bayesian Inference
- Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination
2021/07/05 by Dylan J. Foster, Foster, Dylan J., Akshay Krishnamurthy +1 · 4 citations
Computer Science · Decision Sciences · #Advanced Bandit Algorithms Research #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Algorithms #Machine Learning and Data Classification #Statistics Theory (math.ST)
- Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in Exploration
2025/03/10 by Dylan J. Foster, Foster, Dylan J., Zakaria Mhammedi +3 · 1 voice · 8 citations
#cs.LG #cs.AI #cs.CL #math.ST
- Understanding the Eluder Dimension
2021/04/14 by Gene Li, Li, Gene, Pritish Kamath +5 · 3 citations
Decision Sciences · Computer Science · #Advanced Bandit Algorithms Research #Optimization and Search Problems #Computability, Logic, AI Algorithms
- Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification
2025/02/18 by Dhruv Rohatgi, Adam Block, Rohatgi, Dhruv +7 · 1 voice · 7 citations
Computer Science · #Natural Language Processing Techniques
- Online Learning: Sufficient Statistics and the Burkholder Method
2018/03/20 by Dylan J. Foster, Foster, Dylan J., Alexander Rakhlin +3 · 2 citations
Decision Sciences · Engineering · Computer Science · #Advanced Bandit Algorithms Research #Sparse and Compressive Sensing Techniques #Stochastic Gradient Optimization Techniques
- Learning nonlinear dynamical systems from a single trajectory
2020/04/30 by Dylan J. Foster, Alexander Rakhlin, Foster, Dylan J. +3 · 2 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Engineering · #Control Systems and Identification #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Algorithms #Optimization and Control (math.OC) #Receptor Mechanisms and Signaling #Statistics Theory (math.ST)
- Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL
2023/04/12 by Zakaria Mhammedi, Mhammedi, Zakaria, Dylan J. Foster +3 · 2 citations
Computer Science · #Evolutionary Algorithms and Applications #Machine Learning and Algorithms #Reinforcement Learning in Robotics
- Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression
2023/10/17 by Adam Block, Block, Adam, Dylan J. Foster +7 · 3 citations
Computer Science · #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC) #Reinforcement Learning in Robotics
- ℓ∞ Vector Contraction for Rademacher Complexity
2019/11/15 by Dylan J. Foster, Foster, Dylan J., Alexander Rakhlin +1 · 2 citations
Computer Science · Mathematics · #Computability, Logic, AI Algorithms #Advanced Topology and Set Theory #Complexity and Algorithms in Graphs
- Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient
2023/01/19 by Dylan J. Foster, Noah Golowich, Foster, Dylan J. +3 · 1 citation
Computer Science · Decision Sciences · #Advanced Bandit Algorithms Research #Adversarial Robustness in Machine Learning #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC) #Reinforcement Learning in Robotics #Statistics Theory (math.ST)
- Inference in Sparse Graphs with Pairwise Measurements and Side Information
2017/03/08 by Dylan J. Foster, Foster, Dylan J., Daniel Reichman +3 · 1 citation
Computer Science · Materials Science · #Topological and Geometric Data Analysis #Carbon and Quantum Dots Applications #Complexity and Algorithms in Graphs
- Harnessing Density Ratios for Online Reinforcement Learning
2024/01/18 by Philip Amortila, Amortila, Philip, Dylan J. Foster +7 · 1 citation
Computer Science · #Reinforcement Learning in Robotics #Machine Learning and Data Classification #Software Engineering Research
- Rich-Observation Reinforcement Learning with Continuous Latent Dynamics
2024/05/29 by Yuda Song, Lili Wu, Song, Yuda +5 · 1 citation
Computer Science · #Data Stream Mining Techniques #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Data Classification
- Necessary and Sufficient Oracles: Toward a Computational Taxonomy For Reinforcement Learning
2025/02/12 by Dhruv Rohatgi, Rohatgi, Dhruv, Dylan J. Foster +1 · 1 voice · 1 citation
Computer Science · #Computability, Logic, AI Algorithms #Evolutionary Algorithms and Applications #cs.CC #cs.LG