Alert button
Picture for Elad Hazan

Elad Hazan

Alert button

Second Order Methods for Bandit Optimization and Control

Feb 14, 2024
Arun Suggala, Y. Jennifer Sun, Praneeth Netrapalli, Elad Hazan

Viaarxiv icon

Adaptive Regret for Bandits Made Possible: Two Queries Suffice

Jan 17, 2024
Zhou Lu, Qiuyi Zhang, Xinyi Chen, Fred Zhang, David Woodruff, Elad Hazan

Viaarxiv icon

Chain of LoRA: Efficient Fine-tuning of Language Models via Residual Learning

Jan 08, 2024
Wenhan Xia, Chengwei Qin, Elad Hazan

Viaarxiv icon

Spectral State Space Models

Dec 11, 2023
Naman Agarwal, Daniel Suo, Xinyi Chen, Elad Hazan

Figure 1 for Spectral State Space Models
Figure 2 for Spectral State Space Models
Figure 3 for Spectral State Space Models
Figure 4 for Spectral State Space Models
Viaarxiv icon

AI safety by debate via regret minimization

Dec 08, 2023
Xinyi Chen, Angelica Chen, Dean Foster, Elad Hazan

Viaarxiv icon

An Efficient Interior-Point Method for Online Convex Optimization

Jul 21, 2023
Elad Hazan, Nimrod Megiddo

Figure 1 for An Efficient Interior-Point Method for Online Convex Optimization
Viaarxiv icon

Online Learning for Obstacle Avoidance

Jun 14, 2023
David Snyder, Meghan Booker, Nathaniel Simon, Wenhan Xia, Daniel Suo, Elad Hazan, Anirudha Majumdar

Figure 1 for Online Learning for Obstacle Avoidance
Figure 2 for Online Learning for Obstacle Avoidance
Figure 3 for Online Learning for Obstacle Avoidance
Figure 4 for Online Learning for Obstacle Avoidance
Viaarxiv icon

Online Nonstochastic Model-Free Reinforcement Learning

May 27, 2023
Udaya Ghai, Arushi Gupta, Wenhan Xia, Karan Singh, Elad Hazan

Figure 1 for Online Nonstochastic Model-Free Reinforcement Learning
Figure 2 for Online Nonstochastic Model-Free Reinforcement Learning
Figure 3 for Online Nonstochastic Model-Free Reinforcement Learning
Figure 4 for Online Nonstochastic Model-Free Reinforcement Learning
Viaarxiv icon

Optimal Rates for Bandit Nonstochastic Control

May 24, 2023
Y. Jennifer Sun, Stephen Newman, Elad Hazan

Figure 1 for Optimal Rates for Bandit Nonstochastic Control
Figure 2 for Optimal Rates for Bandit Nonstochastic Control
Viaarxiv icon

Sketchy: Memory-efficient Adaptive Regularization with Frequent Directions

Feb 07, 2023
Vladimir Feinberg, Xinyi Chen, Y. Jennifer Sun, Rohan Anil, Elad Hazan

Figure 1 for Sketchy: Memory-efficient Adaptive Regularization with Frequent Directions
Figure 2 for Sketchy: Memory-efficient Adaptive Regularization with Frequent Directions
Figure 3 for Sketchy: Memory-efficient Adaptive Regularization with Frequent Directions
Figure 4 for Sketchy: Memory-efficient Adaptive Regularization with Frequent Directions
Viaarxiv icon