44 citations · 128 across the 16 of their papers we have counts for
16 papers
Efficient Sequential Calibration with Error Bound
Zihan Zhang
We study the online binary sequential calibration problem. A recent breakthrough by \citet{dagan2024breaking} overcomes the classical \(T^{2/3}\) barrier for calibration error. Bui…
Classification with Deep Neural Networks and Logistic Loss
Zihan Zhang, Lei Shi, Ding-Xuan Zhou
Deep neural networks (DNNs) trained with the logistic loss (i.e., the cross entropy loss) have made impressive advancements in various binary classification tasks. However, general…
Settling the Sample Complexity of Online Reinforcement Learning
Zihan Zhang, Yuxin Chen, Jason D. Lee +1
A central issue lying at the heart of online reinforcement learning (RL) is data efficiency. While a number of recent works achieved asymptotically minimal regret in online RL, the…
Sampling Proper Colorings on Line Graphs Using Colors
Yulin Wang, Chihao Zhang, Zihan Zhang
We prove that the single-site Glauber dynamics for sampling proper -colorings mixes in time on line graphs with vertices and maximum degree when $q>(1+o(1…
Sharper Model-free Reinforcement Learning for Average-reward Markov Decision Processes
Zihan Zhang, Qiaomin Xie
We develop several provably efficient model-free reinforcement learning (RL) algorithms for infinite-horizon average-reward Markov Decision Processes (MDPs). We consider both onlin…
Near-Optimal Regret Bounds for Multi-batch Reinforcement Learning
Zihan Zhang, Yuhang Jiang, Yuan Zhou +1
In this paper, we study the episodic reinforcement learning (RL) problem modeled by finite-horizon Markov Decision Processes (MDPs) with constraint on the number of batches. The mu…
Horizon-Free Reinforcement Learning in Polynomial Time: the Power of Stationary Policies
Zihan Zhang, Xiangyang Ji, Simon S. Du
This paper gives the first polynomial-time algorithm for tabular Markov Decision Processes (MDP) that enjoys a regret bound \emph{independent on the planning horizon}. Specifically…
Improving Non-autoregressive Generation with Mixup Training
Ting Jiang, Shaohan Huang, Zihan Zhang +6
While pre-trained language models have achieved great success on various natural language understanding tasks, how to effectively leverage them into non-autoregressive generation t…
Almost Optimal Batch-Regret Tradeoff for Batch Linear Contextual Bandits
Zihan Zhang, Xiangyang Ji, Yuan Zhou
We study the optimal batch-regret tradeoff for batch linear contextual bandits. For any batch number , number of actions , time horizon , and dimension , we provide an…
A New Metric on Symmetric Group and Applications to Block Permutation Codes
Zihan Zhang
Permutation codes have received a great attention due to various applications. For different applications, one needs permutation codes under different metrics. The generalized Cayl…
Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP
Zihan Zhang, Jiaqi Yang, Xiangyang Ji +1
This paper presents new \emph{variance-aware} confidence sets for linear bandits and linear mixture Markov Decision Processes (MDPs). With the new confidence sets, we obtain the fo…
Nearly Minimax Optimal Reward-free Reinforcement Learning
Zihan Zhang, Simon S. Du, Xiangyang Ji
We study the reward-free reinforcement learning framework, which is particularly suitable for batch reinforcement learning and scenarios where one needs policies for multiple rewar…
Is Reinforcement Learning More Difficult Than Bandits? A Near-optimal Algorithm Escaping the Curse of Horizon
Zihan Zhang, Xiangyang Ji, Simon S. Du
Episodic reinforcement learning and contextual bandits are two widely studied sequential decision-making problems. Episodic reinforcement learning generalizes contextual bandits an…
Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity
Zihan Zhang, Yuan Zhou, Xiangyang Ji
In this paper we consider the problem of learning an -optimal policy for a discounted Markov Decision Process (MDP). Given an MDP with states, actions, the discount fact…
Almost Optimal Model-Free Reinforcement Learning via Reference-Advantage Decomposition
Zihan Zhang, Yuan Zhou, Xiangyang Ji
We study the reinforcement learning problem in the setting of finite-horizon episodic Markov Decision Processes (MDPs) with states, actions, and episode length . We prop…
Regret Minimization for Reinforcement Learning by Evaluating the Optimal Bias Function
Zihan Zhang, Xiangyang Ji
We present an algorithm based on the \emph{Optimism in the Face of Uncertainty} (OFU) principle which is able to learn Reinforcement Learning (RL) modeled by Markov decision proces…