Chengshuai Shi

Fifth-year Ph.D. student Department of Electrical and Computer Engineering University of Virginia Email: cs7ync at virginia dot edu Phone: 434-218-9860 Advisor: Prof. Cong Shen About this picture: My mother drew this Dr. Cat wearing a graduation cap when I was in high school. Now I am working towards a Ph.D. and hopefully, my family can see me wearing it one day:) Since Fall 2021, I have been supported by the generous Bloomberg Data Science Ph.D. fellowship.

Research Interest

I am interested in general machine learning research, and am actively exploring topics related to foundation models, especially in-context learning. My past research was focused on multi-armed bandits (MAB) and reinforcement learning (RL) problems, especially their multi-agent versions. I also have broad interests in distributed learning and federated learning.

News

• 11/2023: One paper accepted to IEEE Transcations on Signal Processing

  • Our paper “Reward Teaching for Federated Multi-Armed Bandits” (with Wei Xiong, Prof. Cong Shen and Prof. Jing Yang) is accepted to IEEE Transcations on Signal Processing, which leverages implicit reward adjustments to guide autonomous bandit agents in a federated multi-armed bandit system.

• 09/2023: Finished a three-month internship at Bloomberg, London!

• 04/2023: Selected to receive the 2023 Charles L. Brown Department of Electrical and Computer Engineering’s Louis T Rader Graduate Research Award!

• 04/2023: One paper accepted to ICML 2023!

  • Our paper “Provably Efficient Offline Reinforcement Learning with Perturbed Data Sources” (with Wei Xiong, Prof. Cong Shen and Prof. Jing Yang) is accepted to be presented at ICML 2022, which provides provably efficient offline RL designs for learning with multiple heterogeneous while related data sources.