Preprints

Optimizing Adaptive Experiments: A Unified Approach to Regret Minimization and Best-Arm Identification
Chao Qin, Daniel Russo
Under review at Operations Research

Adaptive Experimentation in the Presence of Exogenous Nonstationary Variation
Chao Qin, Daniel Russo
Major revision at Management Science

Dual-Directed Algorithm Design for Efficient Pure Exploration
Chao Qin, Wei You
Major revision at Operations Research

A Comment on “Adaptive Treatment Assignment in Experiments for Policy Choice”
Kaito Ariu, Masahiro Kato, Junpei Komiyama, Kenichiro McAlinn, Chao Qin
Conditionally accepted by Econometrica

Journal papers

Rate-Optimal Bayesian Simple Regret in Best-Arm Identification
Junpei Komiyama, Kaito Ariu, Masahiro Kato, Chao Qin
Mathematics of Operations Research, 2023

Stochastic Regret Minimization for Revenue Management Problems with Non-Stationary Demands
Huanan Zhang, Cong Shi, Chao Qin, Cheng Hua
Naval Research Logistics, 2016

A Faster Algorithm for the Resource Allocation Problem with Convex Cost Functions
Cong Shi, Huanan Zhang, Chao Qin
Journal of Discrete Algorithms, 2015

Conference papers

Information-Directed Selection for Top-Two Algorithms
Wei You, Chao Qin, Zihao Wang, Shuoguang Yang
Conference on Learning Theory (COLT) 2023

An Analysis of Ensemble Sampling
Chao Qin, Zheng Wen, Xiuyuan Lu, Benjamin Van Roy
Conference on Neural Information Processing Systems (NeurIPS) 2022

Contextual Information-Directed Sampling
Botao Hao, Tor Lattimore, Chao Qin
International Conference on Machine Learning (ICML) 2022

Open Problem: Optimal Best-Arm Identification with Fixed Budget
Chao Qin
Conference on Learning Theory (COLT) 2022

Improving the Expected Improvement Algorithm
Chao Qin, Diego Klabjan, Daniel Russo
Conference on Neural Information Processing Systems (NeurIPS) 2017

Other papers

From Predictions to Decisions: The Importance of Joint Predictive Distributions
Zheng Wen, Ian Osband, Chao Qin, Xiuyuan Lu, Morteza Ibrahimi, Vikranth Dwaracherla, Mohammad Asghari, Benjamin Van Roy

A Note on “Reinforcement Learning, Bit by Bit”: Sanity Checks on Its Guidance
Chao Qin

Optimal Best Arm Identification in Two-Armed Bandits with a Fixed Budget under a Small Gap
Masahiro Kato, Kaito Ariu, Masaaki Imaizumi, Masahiro Nomura, Chao Qin