b'Jason D. Lee'

research

∙ 07/25/2023

Settling the Sample Complexity of Online Reinforcement Learning

A central issue lying at the heart of online reinforcement learning (RL)...

0 Zihan Zhang, et al. ∙

research

∙ 07/07/2023

Teaching Arithmetic to Small Transformers

Large language models like GPT-4 exhibit emergent capabilities across ge...

0 Nayoung Lee, et al. ∙

research

∙ 07/05/2023

Scaling In-Context Demonstrations with Structured Attention

The recent surge of large language models (LLMs) highlights their abilit...

0 Tianle Cai, et al. ∙

research

∙ 06/21/2023

Sample Complexity for Quadratic Bandits: Hessian Dependent Bounds and Optimal Algorithms

In stochastic zeroth-order optimization, a problem of practical relevanc...

0 Qian Yu, et al. ∙

research

∙ 05/30/2023

Solving Robust MDPs through No-Regret Dynamics

Reinforcement Learning is a powerful framework for training agents to na...

0 Etash Kumar Guha, et al. ∙

research

∙ 05/29/2023

How to Query Human Feedback Efficiently in RL?

Reinforcement Learning with Human Feedback (RLHF) is a paradigm in which...

0 Wenhao Zhan, et al. ∙

research

∙ 05/28/2023

Reward Collapse in Aligning Large Language Models

The extraordinary capabilities of large language models (LLMs) such as C...

4 Ziang Song, et al. ∙

research

∙ 05/27/2023

Fine-Tuning Language Models with Just Forward Passes

Fine-tuning language models (LMs) has yielded success on diverse downstr...

8 Sadhika Malladi, et al. ∙

research

∙ 05/24/2023

Provable Offline Reinforcement Learning with Human Feedback

In this paper, we investigate the problem of offline reinforcement learn...

0 Wenhao Zhan, et al. ∙

research

∙ 05/19/2023

Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability

Recent research has observed that in machine learning optimization, grad...

0 Jingfeng Wu, et al. ∙

research

∙ 05/18/2023

Smoothing the Landscape Boosts the Signal for SGD: Optimal Sample Complexity for Learning Single Index Models

We focus on the task of learning a single index model σ(w^⋆· x) with res...

0 Alex Damian, et al. ∙

research

∙ 05/17/2023

Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning

This paper studies tabular reinforcement learning (RL) in the hybrid set...

1 Gen Li, et al. ∙

research

∙ 05/11/2023

Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks

One of the central questions in the theory of deep learning is to unders...

0 Eshaan Nichani, et al. ∙

research

∙ 05/08/2023

Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning

Policy optimization methods with function approximation are widely used ...

0 Yulai Zhao, et al. ∙

research

∙ 03/03/2023

Can We Find Nash Equilibria at a Linear Rate in Markov Games?

We study decentralized learning in two-player zero-sum discounted Markov...

0 Zhuoqing Song, et al. ∙

research

∙ 02/22/2023

Provably Efficient Reinforcement Learning via Surprise Bound

Value function approximation is important in modern reinforcement learni...

0 Hanlin Zhu, et al. ∙

research

∙ 02/09/2023

Efficient displacement convex optimization with particle gradient descent

Particle gradient descent, which uses particles to represent a probabili...

0 Hadi Daneshmand, et al. ∙

research

∙ 02/05/2023

Refined Value-Based Offline RL under Realizability and Partial Coverage

In offline reinforcement learning (RL) we have no opportunity to explore...

0 Masatoshi Uehara, et al. ∙

research

∙ 01/30/2023

Looped Transformers as Programmable Computers

We present a framework for using transformer networks as universal compu...

0 Angeliki Giannou, et al. ∙

research

∙ 01/27/2023

Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing

It is believed that Gradient Descent (GD) induces an implicit bias towar...

0 Jikai Jin, et al. ∙

research

∙ 10/13/2022

From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent

Stochastic Gradient Descent (SGD) has been the method of choice for lear...

0 Satyen Kale, et al. ∙

research

∙ 09/30/2022

Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability

Traditional analyses of gradient descent show that when the largest eige...

0 Alex Damian, et al. ∙

research

∙ 07/12/2022

PAC Reinforcement Learning for Predictive State Representations

In this paper we study online Reinforcement Learning (RL) in partially o...

5 Wenhao Zhan, et al. ∙

research

∙ 06/30/2022

Neural Networks can Learn Representations with Gradient Descent

Significant theoretical work has established that in specific regimes, n...

0 Alex Damian, et al. ∙

research

∙ 06/24/2022

Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings

We study reinforcement learning with function approximation for large-sc...

6 Masatoshi Uehara, et al. ∙

research

∙ 06/24/2022

Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems

We study Reinforcement Learning for partially observable dynamical syste...

26 Masatoshi Uehara, et al. ∙

research

∙ 06/08/2022

Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials

A recent goal in the theory of deep learning is to identify how neural n...

6 Eshaan Nichani, et al. ∙

research

∙ 06/03/2022

Decentralized Optimistic Hyperpolicy Mirror Descent: Provably No-Regret Learning in Markov Games

We study decentralized policy learning in Markov games where we control ...

14 Wenhao Zhan, et al. ∙

research

∙ 05/18/2022

On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias

We study the dynamics and implicit bias of gradient flow (GF) on univari...

0 Itay Safran, et al. ∙

research

∙ 03/29/2022

Nearly Minimax Algorithms for Linear Bandits with Shared Representation

We give novel algorithms for multi-task and lifelong linear bandits with...

0 Jiaqi Yang, et al. ∙

research

∙ 02/09/2022

Offline Reinforcement Learning with Realizability and Single-policy Concentrability

Sample-efficiency guarantees for offline reinforcement learning (RL) oft...

0 Wenhao Zhan, et al. ∙

research

∙ 12/04/2021

Optimization-Based Separations for Neural Networks

Depth separation results propose a possible theoretical explanation for ...

0 Itay Safran, et al. ∙

research

∙ 10/18/2021

Provable Hierarchy-Based Meta-Reinforcement Learning

Hierarchical reinforcement learning (HRL) has seen widespread interest a...

12 Kurtland Chua, et al. ∙

research

∙ 10/15/2021

Provable Regret Bounds for Deep Online Learning and Control

The use of deep neural networks has been highly successful in reinforcem...

0 Xinyi Chen, et al. ∙

research

∙ 07/30/2021

Towards General Function Approximation in Zero-Sum Markov Games

This paper considers two-player zero-sum finite-horizon Markov games wit...

0 Baihe Huang, et al. ∙

research

∙ 07/14/2021

Going Beyond Linear RL: Sample Efficient Neural Function Approximation

Deep Reinforcement Learning (RL) powered by neural net approximation of ...

4 Baihe Huang, et al. ∙

research

∙ 07/09/2021

Optimal Gradient-based Algorithms for Non-concave Bandit Optimization

Bandit problems with linear or concave reward have been extensively stud...

10 Baihe Huang, et al. ∙

research

∙ 07/06/2021

A Short Note on the Relationship of Information Gain and Eluder Dimension

Eluder dimension and information gain are two widely used methods of com...

5 Kaixuan Huang, et al. ∙

research

∙ 05/24/2021

Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence

Policy optimization, which learns the policy of interest by maximizing t...

7 Wenhao Zhan, et al. ∙

research

∙ 05/05/2021

How Fine-Tuning Allows for Effective Meta-Learning

Representation learning has been widely studied in the context of meta-l...

4 Kurtland Chua, et al. ∙

research

∙ 03/19/2021

Bilinear Classes: A Structural Framework for Provable Generalization in RL

This work introduces Bilinear Classes, a new structural framework, which...

52 Simon S. Du, et al. ∙

research

∙ 02/23/2021

MUSBO: Model-based Uncertainty Regularized and Sample Efficient Batch Optimization for Deployment Constrained Reinforcement Learning

In many contemporary applications such as healthcare, finance, robotics,...

0 DiJia Su, et al. ∙

research

∙ 02/22/2021

A Theory of Label Propagation for Subpopulation Shift

One of the central problems in machine learning is domain adaptation. Un...

4 Tianle Cai, et al. ∙

research

∙ 02/17/2021

Provably Efficient Policy Gradient Methods for Two-Player Zero-Sum Markov Games

Policy gradient methods are widely used in solving two-player zero-sum g...

11 Yulai Zhao, et al. ∙

research

∙ 10/22/2020

Beyond Lazy Training for Over-parameterized Tensor Decomposition

Over-parametrization is an important technique in training neural networ...

0 Xiang Wang, et al. ∙

research

∙ 10/12/2020

How Important is the Train-Validation Split in Meta-Learning?

Meta-learning aims to perform fast adaptation on a new task through lear...

10 Yu Bai, et al. ∙

research

∙ 09/22/2020

Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot

Network pruning is a method for reducing test-time computational resourc...

18 Jingtong Su, et al. ∙

research

∙ 09/21/2020

Generalized Leverage Score Sampling for Neural Networks

Leverage score sampling is a powerful technique that originates from the...

0 Jason D. Lee, et al. ∙

research

∙ 08/03/2020

Predicting What You Already Know Helps: Provable Self-Supervised Learning

Self-supervised representation learning solves auxiliary prediction task...

7 Jason D. Lee, et al. ∙

research

∙ 07/13/2020

Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy

We provide a detailed asymptotic study of gradient flow trajectories and...

0 Edward Moroshko, et al. ∙

Jason D. Lee

Featured Co-authors