Peter L. Bartlett

Minimax Optimal Convergence of Gradient Descent in Logistic Regression via Large and Adaptive Stepsizes JMLR 2026 Risk Comparisons in Linear Regression: Implicit Regularization Dominates Explicit Regularization (Extended Abstract) COLT 2026 On the Statistical Properties of Generative Adversarial Models for Low Intrinsic Data Dimension JMLR 2025 Fast Best-of-N Decoding via Speculative Rejection NeurIPS 2024 In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization NeurIPS 2024 Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency COLT 2024 Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization NeurIPS 2024 Scaling Laws in Linear Regression: Compute, Parameters, and Data NeurIPS 2024 Sharpness-Aware Minimization and the Edge of Stability JMLR 2024 Trained Transformers Learn Linear Models In-Context JMLR 2024 Benign overfitting in ridge regression JMLR 2023 Random Feature Amplification: Feature Learning and Generalization in Neural Networks JMLR 2023 The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks NeurIPS 2023 The Dynamics of Sharpness-Aware Minimization: Bouncing Across Ravines and Drifting Towards Wide Minima JMLR 2023 An Efficient Sampling Algorithm for Non-smooth Composite Potentials JMLR 2022 The Interplay Between Implicit Bias and Benign Overfitting in Two-Layer Linear Networks JMLR 2022 Adversarial Examples in Multi-Layer Random ReLU Networks NeurIPS 2021 Failures of Model-dependent Generalization Bounds for Least-norm Interpolation JMLR 2021 High-Order Langevin Diffusion Yields an Accelerated MCMC Algorithm JMLR 2021 Near Optimal Policy Optimization via REPS NeurIPS 2021 On the Theory of Reinforcement Learning with Once-per-Episode Feedback NeurIPS 2021 When Does Gradient Descent with Logistic Loss Find Interpolating Two-Layer Networks? JMLR 2021 Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems JMLR 2020 Preference learning along multiple criteria: A game-theoretic perspective NeurIPS 2020 Self-Distillation Amplifies Regularization in Hilbert Space NeurIPS 2020 A simple parameter-free and adaptive approach to optimization under a minimal local smoothness assumption ALT 2019 Fast Mean Estimation with Sub-Gaussian Rates COLT 2019 Nearly-tight VC-dimension and Pseudodimension Bounds for Piecewise Linear Neural Networks JMLR 2019 Testing Symmetric Markov Chains Without Hitting COLT 2019 Gen-Oja: Simple & Efficient Algorithm for Streaming Generalized Eigenvector Computation NeurIPS 2018 Horizon-Independent Minimax Linear Regression NeurIPS 2018 Underdamped Langevin MCMC: A non-asymptotic analysis COLT 2018 Acceleration and Averaging in Stochastic Descent Dynamics NeurIPS 2017 Alternating minimization for dictionary learning with random initialization NeurIPS 2017 Near Minimax Optimal Players for the Finite-Time 3-Expert Prediction Problem NeurIPS 2017 Recovery Guarantees for One-hidden-layer Neural Networks ICML 2017 Spectrally-normalized margin bounds for neural networks NeurIPS 2017 Adaptive Averaging in Accelerated Descent Dynamics NeurIPS 2016 A Fast and Reliable Policy Improvement Algorithm AISTATS 2016 Accelerated Mirror Descent in Continuous and Discrete Time NeurIPS 2015 Minimax Fixed-Design Linear Regression COLT 2015 Minimax Time Series Prediction NeurIPS 2015 Efficient Minimax Strategies for Square Loss Games NeurIPS 2014 Large-Margin Convex Polytope Machine NeurIPS 2014 How to Hedge an Option Against an Adversary: Black-Scholes Pricing is Minimax Optimal NeurIPS 2013 Online Learning in Markov Decision Processes with Adversarially Chosen Transition Probability Distributions NeurIPS 2013 The Optimality of Jeffreys Prior for Online Density Estimation and the Asymptotic Normality of Maximum Likelihood Estimators COLT 2012 Blackwell Approachability and No-Regret Learning are Equivalent COLT 2011 Oracle inequalities for computationally budgeted model selection COLT 2011 Information-theoretic lower bounds on the oracle complexity of convex optimization NeurIPS 2009 Classification with a Reject Option using a Hinge Loss JMLR 2008 Exponentiated Gradient Algorithms for Conditional Random Fields and Max-Margin Markov Networks JMLR 2008 AdaBoost is Consistent JMLR 2007 Adaptive Online Gradient Descent NeurIPS 2007 On the Consistency of Multiclass Classification Methods JMLR 2007 Optimistic Linear Programming gives Logarithmic Regret for Irreducible MDPs NeurIPS 2007 Sparseness vs Estimating Conditional Probabilities: Some Asymptotic Results JMLR 2007 AdaBoost is Consistent NeurIPS 2006 Sample Complexity of Policy Search with Known Dynamics NeurIPS 2006 Shifting, One-Inclusion Mistake Bounds and Tight Multiclass Expected Risk Bounds NeurIPS 2006 Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning JMLR 2004 Rademacher and Gaussian Complexities: Risk Bounds and Structural Results JMLR 2002 The Rademacher Complexity of Co-Regularized Kernel Classes AISTATS 1999