Chengshuai Shi

45 papers A* 10A 4B 4Misc 1Journal 25Unranked 1

Year	Rank	Type	Title / Venue / Authors
2025	A	`conf`	Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis. UAI Ruiquan Huang, Donghao Li, Chengshuai Shi, Cong Shen, Jing Yang
2025	J	`jnl`	Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis. CoRR Ruiquan Huang, Donghao Li, Chengshuai Shi, Cong Shen, Jing Yang
2025	A*	`conf`	Building Math Agents with Multi-Turn Iterative Preference Learning. ICLR Wei Xiong, Chengshuai Shi, Jiaming Shen, Aviv Rosenberg, Zhen Qin, Daniele Calandriello, Misha Khalman, Rishabh Joshi, Bilal Piot, Mohammad Saleh, Chi Jin, Tong Zhang, Tianqi Liu
2025	A	`conf`	Cost-Aware Optimal Pairwise Pure Exploration. AISTATS Di Wu, Chengshuai Shi, Ruida Zhou, Cong Shen
2025	J	`jnl`	Cost-Aware Optimal Pairwise Pure Exploration. CoRR Di Wu, Chengshuai Shi, Ruida Zhou, Cong Shen
2025	—	`conf`	From Cross-Task Examples to In-Task Prompts: A Graph-Based Pseudo-Labeling Framework for In-context Learning. EMNLP (Findings) Zihan Chen, Song Wang, Xingbo Fu, Chengshuai Shi, Zhenyu Lei, Cong Shen, Jun-Dong Li
2025	J	`jnl`	From Cross-Task Examples to In-Task Prompts: A Graph-Based Pseudo-Labeling Framework for In-context Learning. CoRR Zihan Chen, Song Wang, Xingbo Fu, Chengshuai Shi, Zhen Lei, Cong Shen, Jundong Li
2025	J	`jnl`	Greedy Sampling Is Provably Efficient for RLHF. CoRR Di Wu, Chengshuai Shi, Jing Yang, Cong Shen
2024	J	`jnl`	Best Arm Identification for Prompt Learning under a Limited Budget. CoRR Chengshuai Shi, Kun Yang, Jing Yang, Cong Shen
2024	J	`jnl`	Building Math Agents with Multi-Turn Iterative Preference Learning. CoRR Wei Xiong, Chengshuai Shi, Jiaming Shen, Aviv Rosenberg, Zhen Qin, Daniele Calandriello, Misha Khalman, Rishabh Joshi, Bilal Piot, Mohammad Saleh, Chi Jin, Tong Zhang, Tianqi Liu
2024	A*	`conf`	Efficient Prompt Optimization Through the Lens of Best Arm Identification. NeurIPS Chengshuai Shi, Kun Yang, Zihan Chen, Jundong Li, Jing Yang, Cong Shen
2024	J	`jnl`	Harnessing the Power of Federated Learning in Federated Contextual Bandits. Trans. Mach. Learn. Res. Chengshuai Shi, Ruida Zhou, Kun Yang, Cong Shen
2024	A*	`conf`	Mixture of Demonstrations for In-Context Learning. NeurIPS Song Wang, Zihan Chen, Chengshuai Shi, Cong Shen, Jundong Li
2024	J	`jnl`	Offline Reinforcement Learning for Wireless Network Optimization With Mixture Datasets. IEEE Trans. Wirel. Commun. Kun Yang, Chengshuai Shi, Cong Shen, Jing Yang, Shu-Ping Yeh, Jaroslaw J. Sydir
2024	A*	`conf`	Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Models. NeurIPS Chengshuai Shi, Kun Yang, Jing Yang, Cong Shen
2024	J	`jnl`	Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Models. CoRR Chengshuai Shi, Kun Yang, Jing Yang, Cong Shen
2023	J	`jnl`	Harnessing the Power of Federated Learning in Federated Contextual Bandits. CoRR Chengshuai Shi, Ruida Zhou, Kun Yang, Cong Shen
2023	A*	`conf`	Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game. ICLR Wei Xiong, Han Zhong, Chengshuai Shi, Cong Shen, Liwei Wang, Tong Zhang
2023	B	`conf`	On High-dimensional and Low-rank Tensor Bandits. ISIT Chengshuai Shi, Cong Shen, Nicholas D. Sidiropoulos
2023	J	`jnl`	On High-dimensional and Low-rank Tensor Bandits. CoRR Chengshuai Shi, Cong Shen, Nicholas D. Sidiropoulos
2023	A*	`conf`	Provably Efficient Offline Reinforcement Learning with Perturbed Data Sources. ICML Chengshuai Shi, Wei Xiong, Cong Shen, Jing Yang
2023	J	`jnl`	Provably Efficient Offline Reinforcement Learning with Perturbed Data Sources. CoRR Chengshuai Shi, Wei Xiong, Cong Shen, Jing Yang
2023	B	`conf`	Reward Teaching for Federated Multi-armed Bandits. ISIT Chengshuai Shi, Wei Xiong, Cong Shen, Jing Yang
2023	J	`jnl`	Reward Teaching for Federated Multi-armed Bandits. CoRR Chengshuai Shi, Wei Xiong, Cong Shen, Jing Yang
2023	J	`jnl`	Reward Teaching for Federated Multiarmed Bandits. IEEE Trans. Signal Process. Chengshuai Shi, Wei Xiong, Cong Shen, Jing Yang
2023	Misc	`conf`	Teaching Reinforcement Learning Agents via Reinforcement Learning. CISS Kun Yang, Chengshuai Shi, Cong Shen
2022	A*	`conf`	A Self-Play Posterior Sampling Algorithm for Zero-Sum Markov Games. ICML Wei Xiong, Han Zhong, Chengshuai Shi, Cong Shen, Tong Zhang
2022	J	`jnl`	A Self-Play Posterior Sampling Algorithm for Zero-Sum Markov Games. CoRR Wei Xiong, Han Zhong, Chengshuai Shi, Cong Shen, Tong Zhang
2022	J	`jnl`	Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game. CoRR Wei Xiong, Han Zhong, Chengshuai Shi, Cong Shen, Liwei Wang, Tong Zhang
2021	A*	`conf`	(Almost) Free Incentivized Exploration from Decentralized Learning Agents. NeurIPS Chengshuai Shi, Haifeng Xu, Wei Xiong, Cong Shen
2021	J	`jnl`	(Almost) Free Incentivized Exploration from Decentralized Learning Agents. CoRR Chengshuai Shi, Haifeng Xu, Wei Xiong, Cong Shen
2021	B	`conf`	An Attackability Perspective on No-Sensing Adversarial Multi-player Multi-armed Bandits. ISIT Chengshuai Shi, Cong Shen
2021	A*	`conf`	Federated Multi-Armed Bandits. AAAI Chengshuai Shi, Cong Shen
2021	J	`jnl`	Federated Multi-Armed Bandits. CoRR Chengshuai Shi, Cong Shen
2021	A	`conf`	Federated Multi-armed Bandits with Personalization. AISTATS Chengshuai Shi, Cong Shen, Jing Yang
2021	J	`jnl`	Federated Multi-armed Bandits with Personalization. CoRR Chengshuai Shi, Cong Shen, Jing Yang
2021	A*	`conf`	Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization. NeurIPS Chengshuai Shi, Wei Xiong, Cong Shen, Jing Yang
2021	J	`jnl`	Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization. CoRR Chengshuai Shi, Wei Xiong, Cong Shen, Jing Yang
2021	J	`jnl`	Multi-Player Multi-Armed Bandits With Collision-Dependent Reward Distributions. IEEE Trans. Signal Process. Chengshuai Shi, Cong Shen
2021	J	`jnl`	Multi-player Multi-armed Bandits with Collision-Dependent Reward Distributions. CoRR Chengshuai Shi, Cong Shen
2021	J	`jnl`	On No-Sensing Adversarial Multi-Player Multi-Armed Bandits With Collision Communications. IEEE J. Sel. Areas Inf. Theory Chengshuai Shi, Cong Shen
2020	A	`conf`	Decentralized Multi-player Multi-armed Bandits with No Collision Information. AISTATS Chengshuai Shi, Wei Xiong, Cong Shen, Jing Yang
2020	J	`jnl`	Decentralized Multi-player Multi-armed Bandits with No Collision Information. CoRR Chengshuai Shi, Wei Xiong, Cong Shen, Jing Yang
2020	J	`jnl`	On No-Sensing Adversarial Multi-player Multi-armed Bandits with Collision Communications. CoRR Chengshuai Shi, Cong Shen
2019	B	`conf`	Privacy-Aware Edge Computing Based on Adaptive DNN Partitioning. GLOBECOM Chengshuai Shi, Lixing Chen, Cong Shen, Linqi Song, Jie Xu