168 citations · 361 across the 47 of their papers we have counts for
13 papers · 1 filter
Optimization-Based Separations for Neural Networks
Itay Safran, Jason D. Lee
Depth separation results propose a possible theoretical explanation for the benefits of deep neural networks over shallower architectures, establishing that the former possess supe…
Provable Hierarchy-Based Meta-Reinforcement Learning
Kurtland Chua, Qi Lei, Jason D. Lee
Hierarchical reinforcement learning (HRL) has seen widespread interest as an approach to tractable learning of complex modular behaviors. However, existing work either assume acces…
Provable Regret Bounds for Deep Online Learning and Control
Xinyi Chen, Edgar Minasyan, Jason D. Lee +1
The theory of deep learning focuses almost exclusively on supervised learning, non-convex optimization using stochastic gradient descent, and overparametrized neural networks. It i…
Optimal Gradient-based Algorithms for Non-concave Bandit Optimization
Baihe Huang, Kaixuan Huang, Sham M. Kakade +4
Bandit problems with linear or concave reward have been extensively studied, but relatively few works have studied bandits with non-concave reward. This work considers a large fami…
A Short Note on the Relationship of Information Gain and Eluder Dimension
Kaixuan Huang, Sham M. Kakade, Jason D. Lee +1
Eluder dimension and information gain are two widely used methods of complexity measures in bandit and reinforcement learning. Eluder dimension was originally proposed as a general…
Towards General Function Approximation in Zero-Sum Markov Games
Baihe Huang, Jason D. Lee, Zhaoran Wang +1
This paper considers two-player zero-sum finite-horizon Markov games with simultaneous moves. The study focuses on the challenging settings where the value function or the model is…
Going Beyond Linear RL: Sample Efficient Neural Function Approximation
Baihe Huang, Kaixuan Huang, Sham M. Kakade +4
Deep Reinforcement Learning (RL) powered by neural net approximation of the Q function has had enormous empirical success. While the theory of RL has traditionally focused on linea…
Near-Optimal Linear Regression under Distribution Shift
Qi Lei, Wei Hu, Jason D. Lee
Transfer learning is essential when sufficient data comes from the source domain, with scarce labeled data from the target domain. We develop estimators that achieve minimax linear…
Label Noise SGD Provably Prefers Flat Global Minimizers
Alex Damian, Tengyu Ma, Jason D. Lee
In overparametrized models, the noise in stochastic gradient descent (SGD) implicitly regularizes the optimization trajectory and determines which local minimum SGD converges to. M…
How Fine-Tuning Allows for Effective Meta-Learning
Kurtland Chua, Qi Lei, Jason D. Lee
Representation learning has been widely studied in the context of meta-learning, enabling rapid learning of new tasks through shared representations. Recent works such as MAML have…
Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence
Wenhao Zhan, Shicong Cen, Baihe Huang +3
Policy optimization, which finds the desired policy by maximizing value functions via optimization techniques, lies at the heart of reinforcement learning (RL). In addition to valu…
Bilinear Classes: A Structural Framework for Provable Generalization in RL
Simon S. Du, Sham M. Kakade, Jason D. Lee +4
This work introduces Bilinear Classes, a new structural framework, which permit generalization in reinforcement learning in a wide variety of settings through the use of function a…
Provably Efficient Policy Optimization for Two-Player Zero-Sum Markov Games
Yulai Zhao, Yuandong Tian, Jason D. Lee +1
Policy-based methods with function approximation are widely used for solving two-player zero-sum games with large state and/or action spaces. However, it remains elusive how to obt…