Publications
Preprints
Spectral State Space Models - Naman Agarwal, Xinyi Chen, Elad Hazan, Daniel Suo
VeLO: Training Versatile Learned Optimizers by Scaling Up - Luke Metz, James Harrison, C. Daniel Freeman, Amil Merchant, Lucas Beyer, James Bradbury, Naman Agrawal, Ben Poole, Igor Mordatch, Adam Roberts, Jascha Sohl-Dickstein
Efficient Adaptive Regret Minimization - Zhou Lu, Elad Hazan
Adaptive Gradient Methods at the Edge of Stability - Jeremy M. Cohen, Behrooz Ghorbani, Shankar Krishnan, Naman Agarwal, Sourabh Medapati, Michal Badura, Daniel Suo, David Cardoze, Zachary Nado, George E. Dahl, Justin Gilmer
Variance-Reduced Conservative Policy Iteration - Naman Agarwal, Brian Bullins, Karan Singh
Adaptive Gradient Methods with Local Guarantees - Zhou Lu, Wenhan Xia, Sanjeev Arora, Elad Hazan
Learning Rate Grafting: Transferability of Optimizer Tuning - Naman Agarwal, Rohan Anil, Elad Hazan, Tomer Koren and Cyril Zhang
Adaptive Regret for Control of Time-Varying Dynamic - Paula Gradu, Elad Hazan, Edgar Minasyan
Publications
2023
Provable Regret Bounds for Deep Online Learning and Control - Xinyi Chen, Edgar Minasyan, Jason D. Lee, Elad Hazan - L4DC 2023
Best of Both Worlds in Online Control: Competitive Ratio and Policy Regret - Gautam Goel, Naman Agarwal, Karan Singh, Elad Hazan - L4DC 2023
Variance-Reduced Conservative Policy Iteration - Naman Agarwal, Brian Bullins, Karan Singh - ALT 2023
Projection-free Adaptive Regret with Membership Oracles - Zhou Lu, Nataly Brukhim, Paula Gradu, Elad Hazan - ALT 2023
Differentially Private and Lazy Online Convex Optimization - Naman Agarwal, Satyen Kale, Karan Singh, Abhradeep Guha Thakurta - COLT 2023
Multi-User Reinforcement Learning with Low Rank Rewards - Dheeraj Nagaraj, Suhas Kowshik, Naman Agarwal, Praneeth Netrapalli, Prateek Jain - ICML 2023
Regret Guarantees for Online Deep Control - Xinyi Chen, Edgar Minyasyan, Jason D. Lee, Elad Hazan - Proceedings of Machine Learning Research
Multi-User Reinforcement Learning with Low Rank Rewards - Udaya Ghai, Arushi Gupta, Wenhan Xia, Karan Singh, Elad Hazan - NeurIPS 2023
Partial Matrix Completion - Elad Hazan, Adam Tauman Kalai, Varun Kanade, Clara Mohri, Y. Jennifer Sun - NeurIPS 2023
Sketchy: Memory-efficient Adaptive Regularization with Frequent Directions - Vladimir Feinberg, Xinyi Chen, Y. Jennifer Sun, Rohan Anil, Elad Hazan - NeurIPS 2023
Optimal Rates for Bandit Nonstochastic Control - Y. Jennifer Sun, Stephen Newman, Elad Hazan - NeurIPS 2023
Online Control for Meta-optimization - Xinyi Chen, Elad Hazan - NeurIPS 2023
2022
A Boosting Approach to Reinforcement Learning - Nataly Brukhim, Elad Hazan, Karan Singh - NeurIPS 2022
Non-convex online learning via algorithmic equivalence - Udaya Ghai, Zhou Lu, Elad Hazan - NeurIPS 2022
A Regret Minimization Approach to Multi-Agent Control - Udaya Ghai, Udari Madhushani, Naomi Leonard, Elad Hazan - ICML 2022 (Also presented at the GMAS Workshop at ICLR 2022 (Oral Presentation + Best Poster))
Pushing the Efficiency-Regret Pareto Frontier for Online Learning of Portfolios and Quantum States - Julian Zimmert, Naman Agarwal, Satyen Kale - COLT 2022
Online Robust Control with Model Misspecification - Xinyi Chen, Udaya Ghai, Elad Hazan, Alexandre Megretski - L4DC 2022 (Also presented at RL Theory Workshop at ICML 2021)
Efficient Methods for Online Multiclass Logistic Regression - Naman Agarwal, Satyen Kale and Julian Zimmert - ALT 2022
Online Target Q-learning with Reverse Experience Replay: Efficiently finding the Optimal Policy for Linear MDPs - Naman Agarwal, Syomantak Chaudhuri, Prateek Jain, Dheeraj Mysore Nagaraj and Praneeth Netrapalli - ICLR 2022
2021
Machine Learning for Mechanical Ventilation Control - Daniel Suo, Cyril Zhang, Paula Gradu, Udaya Ghai , Xinyi Chen, Edgar Minasyan, Naman Agarwal, Karan Singh, Julienne LaChance, Tom Zajdel, Manuel Schottdorf, Daniel Cohen and Elad Hazan - ML4H 2021
The Skellam Mechanism for Differentially Private Federated Learning - Naman Agarwal, Peter Kairouz, Ken Ziyu Liu - Neurips 2021
Generating Adversarial Disturbances for Controller Verification - Udaya Ghai, David Snyder, Anirudh Majumdar, Elad Hazan - L4DC 2021
Black-box control of linear dynamical systems - Xinyi Chen, Elad Hazan - COLT 2021
Boosting Simple Learners - Noga Alon, Alon Gonen, Elad Hazan, Shay Moran - STOC 2021
A Regret Minimization Approach to Iterative Learning Control - Naman Agarwal, Elad Hazan, Karan Singh, Anirudh Majumdar - ICML 2021
Boosting for online convex optimization - Elad Hazan, Karan Singh - ICML 2021
Acceleration via Fractal Learning Rate Schedules - Naman Agarwal, Surbhi Goel, Cyril Zhang - ICML 2021
Online Boosting with Bandit Feedback - Nataly Brukhim, Elad Hazan - ALT 2021
A Deep Conditioning Treatment of Neural Networks - Naman Agarwal, Pranjal Awasthi, Satyen Kale - ALT 2021
2020
Deluca -- A Differentiable Control Library: Environments, Methods, and Benchmarking - Paula Gradu, John Hallman, Daniel Suo, Alex Yu, Naman Agarwal, Udaya Ghai , Karan Singh, Cyril Zhang, Aniruddha Majumdar, Elad Hazan - NeurIPS 2021 DiffCVGP Workshop
Non-stochastic control with bandit feedback - Paula Gradu, John Hallman, Elad Hazan - Neurips 2020
Online Agnostic Boosting via Regret Minimization - Nataly Brukhim, Xinyi Chen, Elad Hazan, Shay Moran - Neurips 2020
A Limitation of the PAC-Bayes Framework - Shay Moran, Roi Livni - Neurips 2020
Learning from Mixtures of Private and Public Populations - Shay Moran, Raef Basilly, Anupama Nandi - Neurips 2020
Stochastic Optimization in Laggard Data Pipelines - Naman Agarwal, Rohan Anil, Tomer Koren, Kunal Talwar, Cyril Zhang - Neurips 2020
Geometric Exploration for Online Control - Orestis Pravlakis, Elad Hazan - Neurips 2020
Self-Tuning Bandits Over unknown Covariate-Shifts - Joe Suk, Samory Kpotufe - Neurips 2020
Boosting for Dynamical Systems - Naman Agarwal, Nataly Brukhim, Elad Hazan, Zhou Lu - ICML 2020
Calibration, Entropy Rates, and Memory in Language Models - Mark Braverman, Xinyi Chen, Sham M. Kakade, Karthik Narasimhan, Cyril Zhang, Yi Zhang - ICML 2020
Private Query Release Assisted by Public Data - Raef Bassily, Albert Cheu, Shay Moran, Aleksandar Nikolov, Jonathan Ullman, Zhiwei Steven Wu - ICML 2020
Improper Learning for Non-stochastic Control - Max Simchowitz, Karan Singh, Elad Hazan - COLT 2020
No-Regret Prediction in Marginally Stable Systems - Udaya Ghai, Holden Lee, Karan Singh, Cyril Zhang, Yi Zhang - COLT 2020
The gradient complexity of linear regression - Mark Braverman, Elad Hazan, Max Simchowitz, Blake Woodworth - COLT 2020
Proper Learning, Helly Number, and An Optimal SVM Bound - Olivier Bousquet, Steve Hanneke, Shay Moran, Nikita Zhivotovskiy - COLT 2020 (Best Paper Award)
Closure Properties for Private Classification and Online Prediction - Noga Alon, Amos Beimel, Shay Moran, Uri Stemmer - COLT 2020
Extreme Tensoring for Low-Memory Preconditioning - Xinyi Chen, Naman Agarwal, Elad Hazan, Cyril Zhang, Yi Zhang - ICLR 2020
The Non-stochastic Control Problem - Elad Hazan, Sham M. Kakade, Karan Singh - ALT 2020
Leverage Score Sampling for Faster Accelerated Regression and ERM - Naman Agarwal, Sham Kakade, Rahul Kidambi, Yin Tat Lee, Praneeth Netrapalli, Aaron Sidford - ALT 2020
Exponentiated Gradient Meets Gradient Descent - Udaya Ghai, Elad Hazan, Yoram Singer - ALT 2020
2019
Logarithmic Regret for Control - Naman Agarwal, Elad Hazan, Karan Singh - Neurips 2019 (Oral) - Best Paper Award at NeurIPS 2019 Optimization Foundations for Reinforcement Learning Workshop
Private Learning Implies Online Learning: An Efficient Reduction - Alon Gonen, Elad Hazan, Shay Moran - Neurips 2019
Learning in Non-convex Games with an Optimization Oracle - Naman Agarwal, Alon Gonen, Elad Hazan - COLT 2019
Provably Efficient Maximum Entropy Exploration - Elad Hazan, Sham M. Kakade, Karan Singh, Abby Van Soest - ICML 2019
Efficient Full-Matrix Adaptive Regularization - Naman Agarwal, Brian Bullins, Xinyi Chen, Elad Hazan, Karan Singh, Cyril Zhang, Yi Zhang - ICML 2019
Online Control with Adversarial Disturbances - Naman Agarwal, Brian Bullins, Elad Hazan, Sham M. Kakade, Karan Singh - ICML 2019
Generalize across tasks: Efficient algorithms for linear representation learning - Brian Bullins, Elad Hazan, Adam Kalai, Roi Livni, ALT 2019