124 citations · 953 across the 47 of their papers we have counts for
23 papers · 1 filter
Sparse PCA with Oracle Property
Quanquan Gu, Zhaoran Wang, Han Liu
In this paper, we study the estimation of the -dimensional sparse principal subspace of covariance matrix in the high-dimensional setting. We aim to recover the oracle princ…
Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality
Tengyu Xu, Zhuoran Yang, Zhaoran Wang +1
Designing off-policy reinforcement learning algorithms is typically a very challenging task, because a desirable iteration update often involves an expectation over an on-policy di…
Risk-Sensitive Deep RL: Variance-Constrained Actor-Critic Provably Finds Globally Optimal Policy
Han Zhong, Xun Deng, Ethan X. Fang +3
While deep reinforcement learning has achieved tremendous successes in various applications, most existing works only focus on maximizing the expected value of total return and thu…
Variational Transport: A Convergent Particle-BasedAlgorithm for Distributional Optimization
Zhuoran Yang, Yufeng Zhang, Yongxin Chen +1
We consider the optimization problem of minimizing a functional defined over a family of probability distributions, where the objective functional is assumed to possess a variation…
Provable Fictitious Play for General Mean-Field Games
Qiaomin Xie, Zhuoran Yang, Zhaoran Wang +1
We propose a reinforcement learning algorithm for stationary mean-field games, where the goal is to learn a pair of mean-field state and stationary policy that constitutes the Nash…
On the Global Optimality of Model-Agnostic Meta-Learning
Lingxiao Wang, Qi Cai, Zhuoran Yang +1
Model-agnostic meta-learning (MAML) formulates meta-learning as a bilevel optimization problem, where the inner level solves each subtask based on a shared prior, while the outer l…
Risk-Sensitive Reinforcement Learning: Near-Optimal Risk-Sample Tradeoff in Regret
Yingjie Fei, Zhuoran Yang, Yudong Chen +2
We study risk-sensitive reinforcement learning in episodic Markov decision processes with unknown transition kernels, where the goal is to optimize the total reward under the risk…
Provably Efficient Causal Reinforcement Learning with Confounded Observational Data
Lingxiao Wang, Zhuoran Yang, Zhaoran Wang
Empowered by expressive function approximators such as neural networks, deep reinforcement learning (DRL) achieves tremendous empirical successes. However, learning expressive func…
Breaking the Curse of Many Agents: Provable Mean Embedding Q-Iteration for Mean-Field Reinforcement Learning
Lingxiao Wang, Zhuoran Yang, Zhaoran Wang
Multi-agent reinforcement learning (MARL) achieves significant empirical successes. However, MARL suffers from the curse of many agents. In this paper, we exploit the symmetry of a…
Can Temporal-Difference and Q-Learning Learn Representation? A Mean-Field Theory
Yufeng Zhang, Qi Cai, Zhuoran Yang +2
Temporal-difference and Q-learning play a key role in deep reinforcement learning, where they are empowered by expressive nonlinear function approximators such as neural networks.…
Upper Confidence Primal-Dual Reinforcement Learning for CMDP with Adversarial Loss
Shuang Qiu, Xiaohan Wei, Zhuoran Yang +2
We consider online learning for episodic stochastically constrained Markov decision processes (CMDPs), which plays a central role in ensuring the safety of reinforcement learning.…
Provably Efficient Safe Exploration via Primal-Dual Policy Optimization
Dongsheng Ding, Xiaohan Wei, Zhuoran Yang +2
We study the Safe Reinforcement Learning (SRL) problem using the Constrained Markov Decision Process (CMDP) formulation in which an agent aims to maximize the expected total reward…
Sample Elicitation
Jiaheng Wei, Zuyue Fu, Yang Liu +3
It is important to collect credible training samples for building data-intensive learning systems (e.g., a deep learning system). Asking people to report complex distributi…
Neural Policy Gradient Methods: Global Optimality and Rates of Convergence
Lingxiao Wang, Qi Cai, Zhuoran Yang +1
Policy gradient methods with actor-critic schemes demonstrate tremendous empirical successes, especially when the actors and critics are parameterized by neural networks. However,…
More Supervision, Less Computation: Statistical-Computational Tradeoffs in Weakly Supervised Learning
Xinyang Yi, Zhaoran Wang, Zhuoran Yang +2
We consider the weakly supervised binary classification problem where the labels are randomly flipped with probability . Although there exist numerous algorithms for this pro…
On the Global Convergence of Actor-Critic: A Case for Linear Quadratic Regulator with Ergodic Cost
Zhuoran Yang, Yongxin Chen, Mingyi Hong +1
Despite the empirical success of the actor-critic algorithm, its theoretical understanding lags behind. In a broader context, actor-critic can be viewed as an online alternating up…
A Communication-Efficient Multi-Agent Actor-Critic Algorithm for Distributed Reinforcement Learning
Yixuan Lin, Kaiqing Zhang, Zhuoran Yang +4
This paper considers a distributed reinforcement learning problem in which a network of multiple agents aim to cooperatively maximize the globally averaged return through communica…
On the Global Convergence of Imitation Learning: A Case for Linear Quadratic Regulator
Qi Cai, Mingyi Hong, Yongxin Chen +1
We study the global convergence of generative adversarial imitation learning for linear quadratic regulators, which is posed as minimax optimization. To address the challenges aris…
A Theoretical Analysis of Deep Q-Learning
Jianqing Fan, Zhaoran Wang, Yuchen Xie +1
Despite the great empirical success of deep reinforcement learning, its theoretical foundation is less well understood. In this work, we make the first attempt to theoretically und…
Off-Policy Evaluation and Learning from Logged Bandit Feedback: Error Reduction via Surrogate Policy
Yuan Xie, Boyi Liu, Qiang Liu +3
When learning from a batch of logged bandit feedback, the discrepancy between the policy to be learned and the off-policy training data imposes statistical and computational challe…
On Tighter Generalization Bound for Deep Neural Networks: CNNs, ResNets, and Beyond
Xingguo Li, Junwei Lu, Zhaoran Wang +2
We establish a margin based data dependent generalization error bound for a general family of deep neural networks in terms of the depth and width, as well as the Jacobian of the n…
Multi-Agent Reinforcement Learning via Double Averaging Primal-Dual Optimization
Hoi-To Wai, Zhuoran Yang, Zhaoran Wang +1
Despite the success of single-agent reinforcement learning, multi-agent reinforcement learning (MARL) remains challenging due to complex interactions between agents. Motivated by d…
Symmetry, Saddle Points, and Global Optimization Landscape of Nonconvex Matrix Factorization
Xingguo Li, Junwei Lu, Raman Arora +4
We propose a general theory for studying the \xl{landscape} of nonconvex \xl{optimization} with underlying symmetric structures \tz{for a class of machine learning problems (e.g.,…