Peng Chen

About

I am a Ph.D. student in Computer Science at Zhejiang University, advised by Prof. Shuiguang Deng with co-advisors Profs. Hailiang Zhao and Xueyan Tang (NTU). Previously, I was affiliated with Alibaba Cloud, working on distributed systems and congestion control algorithms. My research focuses on the theoretical foundations of robust decision-making across generalized AI+X domains (e.g., AI+Systems), with an emphasis on algorithmic design. I am also interested in algorithmic competitions.

Research

ML for Algorithms while Guaranteeing Robustness ML for Systems while Guaranteeing Robustness

Selected Publications

[NeurIPS 2025] Robustifying Learning-Augmented Caching Efficiently without Compromising 1-Consistency
Peng Chen, Hailiang Zhao*, Jiaji Zhang, Xueyan Tang, Yixuan Wang, Shuiguang Deng*
Abstract: This paper proposes a lightweight framework named Guard (Guarding the system against modeling errors serves as one of the guidelines for research in ML for Systems.) that efficiently improves the robustness of a broad class of ML-based caching algorithms while preserving their 1-consistency.
[NeurIPS 2024] Learning-Augmented Algorithms for the Bahncard Problem
Hailiang Zhao, Xueyan Tang*, Peng Chen, and Shuiguang Deng
Abstract: This paper introduces PFSUM, a learning-augmented algorithm that leverages both historical data and short-term future information to enhance online decision-making.

Awards

What I Feed My Research

Learning-augmented Algorithms Machine Learning for Systems

Contact

Email: naturechenpeng@gmail.com, pgchen@zju.edu.cn