Elad Hazan

Provable Length Generalization in Sequence Prediction via Spectral Filtering ICML 2025 Online Control in Population Dynamics NIPS 2024 Open Problem: Black-Box Reductions and Adaptive Gradient Methods for Nonconvex Optimization COLT 2024 Second Order Methods for Bandit Optimization and Control COLT 2024 Adaptive Regret for Bandits Made Possible: Two Queries Suffice ICLR 2024 Online Learning for Obstacle Avoidance CORL 2023 Sketchy: Memory-efficient Adaptive Regularization with Frequent Directions NIPS 2023 Online Control for Meta-optimization NIPS 2023 Partial Matrix Completion NIPS 2023 Optimal Rates for Bandit Nonstochastic Control NIPS 2023 Online Nonstochastic Model-Free Reinforcement Learning NIPS 2023 Best of Both Worlds in Online Control: Competitive Ratio and Policy Regret L4DC 2023 Regret Guarantees for Online Deep Control L4DC 2023 Adaptive Regret for Control of Time-Varying Dynamics L4DC 2023 Projection-free Adaptive Regret with Membership Oracles ALT 2023 A Regret Minimization Approach to Multi-Agent Control ICML 2022 Non-convex online learning via algorithmic equivalence NIPS 2022 A Boosting Approach to Reinforcement Learning NIPS 2022 Robust Online Control with Model Misspecification L4DC 2022 Multiclass Boosting and the Cost of Weak Learning NIPS 2021 Online Control of Unknown Time-Varying Dynamical Systems NIPS 2021 Generating Adversarial Disturbances for Controller Verification L4DC 2021 Boosting for Online Convex Optimization ICML 2021 Online Boosting with Bandit Feedback ALT 2021 Black-Box Control for Linear Dynamical Systems COLT 2021 A Regret Minimization Approach to Iterative Learning Control ICML 2021 Faster Projection-free Online Learning COLT 2020 Online Agnostic Boosting via Regret Minimization NIPS 2020 Geometric Exploration for Online Control NIPS 2020 Non-Stochastic Control with Bandit Feedback NIPS 2020 Boosting for Control of Dynamical Systems ICML 2020 Extreme Tensoring for Low-Memory Preconditioning ICLR 2020 Exponentiated Gradient Meets Gradient Descent ALT 2020 The Nonstochastic Control Problem ALT 2020 Improper Learning for Non-Stochastic Control COLT 2020 The Gradient Complexity of Linear Regression COLT 2020 Private Learning Implies Online Learning: An Efficient Reduction NIPS 2019 Logarithmic Regret for Online Control NIPS 2019 Generalize Across Tasks: Efficient Algorithms for Linear Representation Learning ALT 2019 Provably Efficient Maximum Entropy Exploration ICML 2019 Online Control with Adversarial Disturbances ICML 2019 Efficient Full-Matrix Adaptive Regularization ICML 2019 Learning in Non-convex Games with an Optimization Oracle COLT 2019 Online Learning of Quantum States NIPS 2018 Spectral Filtering for General Linear Dynamical Systems NIPS 2018 Lower Bounds for Higher-Order Convex Optimization COLT 2018 Open problem: Improper learning of mixtures of Gaussians COLT 2018 Hyperparameter optimization: a spectral approach ICLR 2018 On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization ICML 2018 Online Improper Learning with an Approximation Oracle NIPS 2018 Second-Order Stochastic Optimization for Machine Learning in Linear Time JMLR 2017 Efficient Regret Minimization in Non-Convex Games ICML 2017 Linear Convergence of a Frank-Wolfe Type Algorithm over Trace-Norm Balls NIPS 2017 Learning Linear Dynamical Systems via Spectral Filtering NIPS 2017 A Non-generative Framework and Convex Relaxations for Unsupervised Learning NIPS 2016 The Limits of Learning with Missing Data NIPS 2016 Online Learning with Low Rank Experts COLT 2016 Optimal Black-Box Reductions Between Optimization Objectives NIPS 2016 Variance-Reduced and Projection-Free Stochastic Optimization ICML 2016 Faster Convex Optimization: Simulated Annealing with an Efficient Universal Barrier ICML 2016 Faster Eigenvector Computation via Shift-and-Invert Preconditioning ICML 2016 Volumetric Spanners: An Efficient Exploration Basis for Learning JMLR 2016 Variance Reduction for Faster Non-Convex Optimization ICML 2016 On Graduated Optimization for Stochastic Non-Convex Problems ICML 2016 Beyond Convexity: Stochastic Quasi-Convex Optimization NIPS 2015 Conference on Learning Theory 2015: Preface COLT 2015 Classification with Low Rank and Missing Data ICML 2015 Faster Rates for the Frank-Wolfe Method over Strongly-Convex Sets ICML 2015 Online Learning of Eigenvectors ICML 2015 Online Time Series Prediction with Missing Data ICML 2015 Online Gradient Boosting NIPS 2015 Online Learning for Adversaries with Memory: Price of Past Mistakes NIPS 2015 Volumetric Spanners: an Efficient Exploration Basis for Learning COLT 2014 Bandit Convex Optimization: Towards Tight Bounds NIPS 2014 The Blinded Bandit: Learning with Adaptive Feedback NIPS 2014 Hard-Margin Active Linear Regression ICML 2014 Beyond the Regret Minimization Barrier: Optimal Algorithms for Stochastic Strongly-Convex Optimization JMLR 2014 Logistic Regression: Tight Bounds for Stochastic and Online Optimization COLT 2014 Better Rates for Any Adversarial Deterministic MDP ICML 2013 Online Learning for Time Series Prediction COLT 2013 Online Submodular Minimization JMLR 2012 Near-Optimal Algorithms for Online Matrix Prediction COLT 2012 A Polylog Pivot Steps Simplex Algorithm for Classification NIPS 2012 (weak) Calibration is Computationally Hard COLT 2012 A simple multi-armed bandit algorithm with optimal variation-bounded regret COLT 2011 Beating SGD: Learning SVMs in Sublinear Time NIPS 2011 Blackwell Approachability and No-Regret Learning are Equivalent COLT 2011 Beyond the regret minimization barrier: an optimal algorithm for stochastic strongly-convex optimization COLT 2011 Approximating Semidefinite Programs in Sublinear Time NIPS 2011 Better Algorithms for Benign Bandits JMLR 2011 Adaptive Subgradient Methods for Online Learning and Stochastic Optimization JMLR 2011 Newtron: an Efficient Bandit algorithm for Online Multiclass Prediction NIPS 2011 Beyond Convexity: Online Submodular Minimization NIPS 2009 On Stochastic and Worst-case Models for Investing NIPS 2009 Adaptive Online Gradient Descent NIPS 2007 Computational Equivalence of Fixed Points and No Regret Algorithms, and Convergence to Equilibria NIPS 2007