Welcome to Qining Zhang's Homepage

Qining Zhang (张启宁) Ph.D. Candidate Department of Electrical Engineering and Computer Science University of Michigan, Ann Arbor Address: 1301 Beal Ave, Ann Arbor, MI, USA, 48105 E-mail: qiningz AT umich Dot edu

About me

Hi! I am a 5th-year Ph.D. student at the Department of Electrical Engineering and Computer Science of the University of Michigan - Ann Arbor, USA. I'm very fortunate to be advised by Prof. Lei Ying. Before joining Michigan, I received my bachelor's degree from Tsinghua University, China, in 2021, mentored by Prof. Jintao Wang and Dr. Haoyue Tang. I also had a wonderful summer in 2024 as an Applied Scientist Intern with Amazon Search Experience Science team, mentored by Dr. Yi Liu and Dr. Tanner Fiez.

Research

My research explores the mathematical foundation of stochastic systems, algorithms, and general applied probability problems. My research interests include:

• Reinforcement learning and optimization;

• Sequential decision-making, bandits, experimental design, and online optimization;

• Stochstic control and network optimization.

Publications

Preprints

1. Provable Reinforcement Learning from Human Feedback with an Unknown Link Function
   Qining Zhang, Lei Ying.
   Under Review, 2025, a short version is accepted at the Neurips 2025 MLxOR Workshop.

2. Multi-Metric Adaptive Experimental Design under Fixed Budget with Validation
   Qining Zhang, Tanner Fiez, Yi Liu, Wenyang Liu.
   Under Review, 2025.

Conference Papers

1. Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference
   Qining Zhang, Lei Ying.
   International Conference on Learning Representations (ICLR), 2025. (Acceptence Rate: 32.1%)

2. Reinforcement Learning from Human Feedback without Reward Inference: Model-Free Algorithm and Instance-Dependent Analysis
   Qining Zhang, Honghao Wei, Lei Ying.
   Reinforcement Learning Conference (RLC), 2024.

3. Cost Aware Best Arm Identification
   Kellen Kanarios, Qining Zhang, Lei Ying.
   Reinforcement Learning Conference (RLC), 2024.

4. Deep Reinforcement Learning for Early Diagnosis of Lung Cancer
   Yifan Wang, Qining Zhang, Chuan Zhou, Lei Ying.
   AAAI Conference on Artificial Intelligence (AAAI), 2024. (Acceptence Rate: 24.2%)

5. Fast and Regret Optimal Best Arm Identification: Fundamental Limits and Low-Complexity Algorithms
   Qining Zhang, Lei Ying.
   Conference on Neural Information Processing Systems (NeurIPS), 2023. (Acceptence Rate: 26.1%)

6. On Low-Complexity Quickest Intervention of Mutated Diffusion Processes Through Local Approximation
   Qining Zhang, Honghao Wei, Weina Wang, Lei Ying.
   ACM Mobihoc, 2022. (Acceptence Rate: 20%)

7. Online Optimizing Multi-user Interference Network Utility with Unknown CSI under Budget Constraint
   Yuchao Chen, Jintao Wang, Qining Zhang, Feifei Gao.
   IEEE Wireless Communications and Networking Conference (WCNC), 2022.

8. Minimizing the Age of Synchronization in Power-constrained Wireless Networks with Unreliable Time-varying Channels
   Qining Zhang, Haoyue Tang, Jintao Wang.
   Age-of-Information Workshops, IEEE INFOCOM, 2020.

Journal Papers

1. Reinforcement Learning from Human Feedback without Reward Inference: Model-Free Algorithm and Instance-Dependent Analysis
   Qining Zhang, Honghao Wei, Lei Ying.
   Reinforcement Learning Journal (RLJ), 2024.

2. Cost Aware Best Arm Identification
   Kellen Kanarios, Qining Zhang, Lei Ying.
   Reinforcement Learning Journal (RLJ), 2024.

3. Online Utility Optimization in Multi-User Interference Networks Under a Long-Term Budget Constraint
   Yuchao Chen, Jintao Wang, Qining Zhang, Feifei Gao.
   IEEE Transactions on Vehicular Technology, 2022.

Technical Report

1. Towards Understanding the Fundamental Limits of Offline Stochastic Bandits with Constraints
   Qining Zhang*, Zixian Yang*, Cong Ma, Lei Ying.
   Equal Contribution, 2022.