Peter Bartlett

Statistical Guarantees for Unpaired Image-to-Image Cross-Domain Analysis using GANs AISTATS 2025 Contextual Bandits with Stage-wise Constraints JMLR 2025 Gradient Descent Converges Arbitrarily Fast for Logistic Regression via Large and Adaptive Stepsizes ICML 2025 Benefits of Early Stopping in Gradient Descent for Overparameterized Logistic Regression ICML 2025 Implicit Bias of Gradient Descent for Non-Homogeneous Deep Networks ICML 2025 Implicit Diffusion: Efficient optimization through stochastic sampling AISTATS 2025 How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression? ICLR 2024 A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional Data ICLR 2024 Can a transformer represent a Kalman filter? L4DC 2024 An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Bandit ALT 2023 A Complete Characterization of Linear Estimators for Offline Policy Evaluation JMLR 2023 Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data ICLR 2023 Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization COLT 2023 Optimal Mean Estimation without a Variance COLT 2022 Generalization Bounds for Data-Driven Numerical Linear Algebra COLT 2022 Optimal and instance-dependent guarantees for Markovian linear stochastic approximation COLT 2022 Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data COLT 2022 Dropout: Explicit Forms and Capacity Control ICML 2021 Towards a Dimension-Free Understanding of Adaptive Linear Control COLT 2021 When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations? COLT 2021 Stochastic Bandits with Linear Constraints AISTATS 2021 OSOM: A simultaneously optimal algorithm for multi-armed and linear contextual bandits AISTATS 2020 On Approximate Thompson Sampling with Langevin Algorithms ICML 2020 Greedy Convex Ensemble IJCAI 2020 Langevin Monte Carlo without smoothness AISTATS 2020 Accelerated Message Passing for Entropy-Regularized MAP Inference ICML 2020 Stochastic Gradient and Langevin Processes ICML 2020 Best of many worlds: Robust model selection for online supervised learning AISTATS 2019 Online learning with kernel losses ICML 2019 Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems AISTATS 2019 Scale-free adaptive planning for deterministic dynamics & discounted rewards ICML 2019 POLITEX: Regret Bounds for Policy Iteration using Expert Prediction ICML 2019 Rademacher Complexity for Adversarially Robust Generalization ICML 2019 Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning ICML 2019 Best of both worlds: Stochastic & adversarial best-arm identification COLT 2018 Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks ICML 2018 On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo ICML 2018 Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates ICML 2018 Gradient Diversity: a Key Ingredient for Scalable Distributed Learning AISTATS 2018 FLAG n’ FLARE: Fast Linearly-Coupled Adaptive Gradient Methods AISTATS 2018 Convergence of Langevin MCMC in KL-divergence ALT 2018 Hit-and-Run for Sampling and Planning in Non-Convex Spaces AISTATS 2017 Improved Learning Complexity in Combinatorial Pure Exploration Bandits AISTATS 2016 Large-Scale Markov Decision Problems with KL Control Cost and its Application to Crowdsourcing ICML 2015 Prediction with Limited Advice and Multiarmed Bandits with Paid Observations ICML 2014 Linear Programming for Large-Scale Markov Decision Problems ICML 2014 Tracking Adversarial Targets ICML 2014 Horizon-Independent Optimal Prediction with Log-Loss in Exponential Families COLT 2013 Open Problem: Adversarial Multiarmed Bandits with Limited Advice COLT 2013 Exchangeability Characterizes Optimality of Sequential Normalized Maximum Likelihood and Bayesian Prediction with Jeffreys Prior AISTATS 2012 Optimal Allocation Strategies for the Dark Pool Problem AISTATS 2010 Learning the Kernel Matrix with Semidefinite Programming JMLR 2004