Satyen Kale

Efficient stagewise pretraining via progressive subnetworks ICLR 2025 Improved Differentially Private and Lazy Online Convex Optimization: Lower Regret without Smoothness Requirements ICML 2024 Semi-supervised Group DRO: Combating Sparsity with Unlabeled Data ALT 2024 Beyond Uniform Lipschitz Condition in Differentially Private Optimization ICML 2023 Differentially Private and Lazy Online Convex Optimization COLT 2023 Efficient Training of Language Models using Few-Shot Learning ICML 2023 On the Convergence of Federated Averaging with Cyclic Client Participation ICML 2023 Agnostic Learnability of Halfspaces via Logistic Loss ICML 2022 Efficient Methods for Online Multiclass Logistic Regression ALT 2022 Federated Functional Gradient Boosting AISTATS 2022 From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent NeurIPS 2022 Private Matrix Approximation and Geometry of Unitary Orbits COLT 2022 Pushing the Efficiency-Regret Pareto Frontier for Online Learning of Portfolios and Quantum States COLT 2022 Reproducibility in Optimization: Theoretical Framework and Limits NeurIPS 2022 Self-Consistency of the Fokker Planck Equation COLT 2022 A Deep Conditioning Treatment of Neural Networks ALT 2021 Breaking the centralized barrier for cross-device federated learning NeurIPS 2021 Learning with User-Level Privacy NeurIPS 2021 SGD: The Role of Implicit Regularization, Batch-size and Multiple-epochs NeurIPS 2021 Estimating Training Data Influence by Tracing Gradient Descent NeurIPS 2020 PAC-Bayes Learning Bounds for Sample-Dependent Priors NeurIPS 2020 SCAFFOLD: Stochastic Controlled Averaging for Federated Learning ICML 2020 Algorithmic Learning Theory 2019: Preface ALT 2019 Breaking the Glass Ceiling for Embedding-Based Classifiers for Large Output Spaces NeurIPS 2019 Escaping Saddle Points with Adaptive Gradient Methods ICML 2019 Hypothesis Set Stability and Generalization NeurIPS 2019 Stochastic Negative Mining for Learning with Large Output Spaces AISTATS 2019 Adaptive Methods for Nonconvex Optimization NeurIPS 2018 Logistic Regression: The Importance of Being Improper COLT 2018 Loss Decomposition for Fast Learning in Large Output Spaces ICML 2018 Online Learning of Quantum States NeurIPS 2018 On the Convergence of Adam and Beyond ICLR 2018 Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIP ICML 2017 Parameter-Free Online Learning via Model Selection NeurIPS 2017 Preface: Conference on Learning Theory (COLT), 2017 COLT 2017 Hardness of Online Sleeping Combinatorial Optimization Problems NeurIPS 2016 Online Sparse Linear Regression COLT 2016 Optimal and Adaptive Algorithms for Online Boosting IJCAI 2016 Online Gradient Boosting NeurIPS 2015 Optimal and Adaptive Algorithms for Online Boosting ICML 2015 Beyond the Regret Minimization Barrier: Optimal Algorithms for Stochastic Strongly-Convex Optimization JMLR 2014 Multiarmed Bandits With Limited Expert Advice COLT 2014 Open Problem: Efficient Online Sparse Regression COLT 2014 Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits ICML 2014 Adaptive Market Making via Online Learning NeurIPS 2013 Bargaining for Revenue Shares on Tree Trading Networks IJCAI 2013 Contextual Bandit Learning with Predictable Rewards AISTATS 2012 Near-Optimal Algorithms for Online Matrix Prediction COLT 2012 Online Submodular Minimization JMLR 2012 A simple multi-armed bandit algorithm with optimal variation-bounded regret COLT 2011 Better Algorithms for Benign Bandits JMLR 2011 Beyond the regret minimization barrier: an optimal algorithm for stochastic strongly-convex optimization COLT 2011 Newtron: an Efficient Bandit algorithm for Online Multiclass Prediction NeurIPS 2011 Non-Stochastic Bandit Slate Problems NeurIPS 2010 Beyond Convexity: Online Submodular Minimization NeurIPS 2009 On Stochastic and Worst-case Models for Investing NeurIPS 2009 Computational Equivalence of Fixed Points and No Regret Algorithms, and Convergence to Equilibria NeurIPS 2007