About
I am currently an Assistant Professor in the Department of Electrical and Computer Engineering
of Wayne State University.
I received my Ph.D. in ECE at Ohio State University, advised by Prof. Ness Shroff. Prior to that, I graduated from BUPT with
a B.S. and Tsinghua University with an M.S., both in
Electrical Engineering.
I have also been a machine learing engineer intern at Facebook and a research intern at Alibaba, USA advised by Jian Tan.
I am looking for self-motivated Ph.D. students for Spring'24 and Fall'24. Please drop me an email with your CV and transcripts, if you have an interest.
Research Overview
My research interests include both machine learning and stochastic systems. On the learning side, I mainly focus on bandits and reinforcement learning with a focus on differential privacy. On the stochastic systems side, I primarily work on load balancing problems with applications in data centers and cloud computing.
Selected Preprints
(* denotes equal contributions)
Multi-Armed Bandits with Local Differential Privacy Wenbo Ren, Xingyu Zhou, Jia Liu and Ness Shroff Arxiv
On the Fenchel Duality between Strong Convexity and Lipschitz Continuous Gradient Xingyu Zhou Arxiv, [blog post]
A Note on Stein’s Method for Heavy-Traffic Analysis Xingyu Zhou and Ness Shroff Arxiv
Selected Publications
(* denotes equal contributions)
On Differentially Private Federated Linear Contextual Bandits Xingyu Zhou and Sayak Ray Chowdhury ICLR 2024 Short version accepted by FL Workshop @ ICML 2023 and TPDP'23
Differentially Private Reward Estimation with Preference Feedback Sayak Ray Chowdhury*, Xingyu Zhou*, Nagarajan Natarajan AISTATS 2024
Towards Achieving Sub-linear Regret and Hard Constraint Violation in Model-free RL Arnob Ghosh, Xingyu Zhou, Ness Shroff AISTATS 2024
On Private and Robust Bandits Yulian Wu*, Xingyu Zhou*, Youming Tao, Di Wang NeurIPS 2023
Understanding the Role of Feedback in Online Learning with Switching Costs Duo Cheng, Xingyu Zhou, Bo Ji ICML 2023
Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards Yulian Wu, Xingyu Zhou, Sayak Ray Chowdhury, Di Wang ICML 2023
Distributed Differential Privacy in Multi-Armed Bandits Sayak Ray Chowdhury*, Xingyu Zhou* ICLR 2023, [slides] Short version accepted by Trustworthy and Socially Responsible ML (TSRML) at NeurIPS 2022
Achieving Sub-linear Regret in Infinite Horizon Average Reward Constrained MDP with Linear Function Approximation Arnob Ghosh, Xingyu Zhou, Ness Shroff ICLR 2023
(Private) Kernelized Bandits with Distributed Biased Feedback Fengjiao Li, Xingyu Zhou, Bo Ji ACM Sigmetrics 2023 (acceptance rate ~ 21.8%), [slides]
On Kernelized Multi-Armed Bandits with Constraints Xingyu Zhou, Bo Ji NeurIPS 2022 (acceptance rate ~ 25.6%), [slides]
Provably Efficient Model-Free Constrained RL with Linear Function Approximation Arnob Ghosh, Xingyu Zhou, Ness Shroff NeurIPS 2022 (acceptance rate ~ 25.6%)
Differentially Private Linear Bandits with Partial Distributed Feedback Fengjiao Li, Xingyu Zhou, Bo Ji WiOpt 2022 (Best Student Paper)
Interference Constrained Beam Alignment for Time-Varying Channels via Kernelized Bandits Yuntian Deng, Xingyu Zhou, Arnob Ghosh, Abhishek Gupta, Ness Shroff WiOpt 2022 (Best Student Paper Runner-Up)
Shuffle Private Linear Contextual Bandits Sayak Ray Chowdhury*, Xingyu Zhou* ICML 2022 (acceptance rate ~ 22%), [slides]
Weighted Gaussian Process Bandits for Non-stationary Environments Yuntian Deng, Xingyu Zhou, Baekjin Kim, Ambuj Tewari, Abhishek Gupta, Ness Shroff AISTATS 2022 (acceptance rate ~ 28%)
Differentially Private Reinforcement Learning with Linear Function Approximation Xingyu Zhou ACM Sigmetrics/IFIP Performance 2022 (acceptance rate ~ 20%)
Differentially Private Regret Minimization in Episodic Markov Decision Processes Sayak Ray Chowdhury*, Xingyu Zhou* AAAI 2022, Oral Presentation (oral acceptance rate ~ 4.6%)
Adaptive Control of Differentially Private Linear Quadratic Systems Sayak Ray Chowdhury*, Xingyu Zhou* and Ness Shroff ISIT 2021
Local Differential Privacy for Bayesian Optimization Xingyu Zhou and Jian Tan AAAI 2021 (acceptance rate ~ 21%)
No-Regret Algorithms for Time-Varying Bayesian Optimization Xingyu Zhou and Ness Shroff CISS 2021 (invited)
Optimal Load Balancing with Locality Constraints Wentao Weng, Xingyu Zhou, and R. Srikant ACM Sigmetrics 2021 (acceptance rate ~ 12%)
Asymptotically Optimal Load Balancing in Large-scale Heterogeneous Systems with Multiple Dispatchers Xingyu Zhou, Ness Shroff and Adam Wierman IFIP Performance 2020
Heavy-traffic Delay Optimality in Pull-based Load Balancing Systems: Necessary and Sufficient Conditions Xingyu Zhou, Jian Tan and Ness Shroff ACM Sigmetrics/IFIP Performance 2019 (acceptance rate ~ 16%)
Flexible Load Balancing with Multi-dimensional State-space Collapse: Throughput and Heavy-traffic Delay Optimality Xingyu Zhou, Jian Tan and Ness Shroff IFIP Performance 2018
Degree of Queue Imbalance: Overcoming the Limitation of Heavy-traffic Delay Optimality in Load Balancing Systems Xingyu Zhou*, Fei Wu*, Jian Tan, Kannan Srinivasan, and Ness Shroff ACM Sigmetrics 2018 (acceptance rate ~ 20%)
Designing Low-Complexity Heavy-Traffic Delay-Optimal Load Balancing Schemes: Theory to Algorithms Xingyu Zhou, Fei Wu, Jian Tan, Yin Sun, Ness Shroff ACM Sigmetrics 2018 (acceptance rate ~ 20%)
Teaching
ECE 7995: Online Decision Making, Wayne State University, Fall-2021.
ECE 4050/CSC 5050: Algorithms and Data Structures, Wayne State University, Winter-2021,2022, Fall-2022.
ECE 2050: Object-Oriented Programming for ECE, Wayne State University, Fall-2022, 2023.
Invited Talks
On Differentially Private Federated Linear Contextual Bandits AI-EDGE Seminar (hosted by Prof. Ness Shroff), Mar. 2023 pdf Robotics and Control Seminar (hosted by Prof. Vaibhav Srivastava), Sep. 2023 pdf
Shuffle Private Linear Contextual Bandits pdf UCLA Big Data and Machine Learning Seminar (hosted by Prof. Quanquan Gu), Jun. 2022
Stein’s Method for Heavy-traffic Analysis: Load Balancing and Scheduling pdf YEQT workshop, Virtual, Jun. 2021
Stein’s Method for Heavy-traffic Analysis With Applications in Load Balancing And Scheduling pdf INFORMS Annual Meeting, Virtual, Oct. 2021
Asymptotically Optimal Load Balancing in Large-scale Heterogeneous Systems with Multiple Dispatchers pdf INFORMS Annual Meeting, Virtual, Oct. 2020
Heavy-traffic Delay Optimality in Pull-based Load Balancing Systems: Necessary and Sufficient Conditions INFORMS Annual Meeting, Seattle, Oct. 2019
Heavy-traffic Delay Optimality in Pull-based Load Balancing Systems: Necessary and Sufficient Conditions pdf RSRG Seminar (hosted by Prof. Adam Wierman), Caltech, Feb. 2019
Load balancing in heavy traffic: Theory and algorithms SQUALL seminar (hosted by Prof. Mor Harchol-Balter), CMU, Sep. 2018
Award
Best Student Paper Award, WiOpt 2022
Best Student Paper Runner-Up, WiOpt 2022
NSF CISE Research Initiation Initiative Award
Presidential Fellowship, The Ohio State University 2019 (the highest honor at OSU).
Student Travel Grant, ACM Sigmetrics 2018, 2019
Student Travel Grant, IFIP Performance 2018.
Excellent Dissertation Award, Chinese Institute of Electronics, 2016
Outstanding Graduate Award of Beijing city, 2012 and 2015.
Outstanding Graduate Award, BUPT and Tsinghua University, 2012 and 2015.
Distinguished Dissertation Award, BUPT and Tsinghua University, 2012 and 2015.
Academic Rising Star Award, Electrical Engineering, Tsinghua University, 2015.
“The December 9th” Scholarship, Tsinghua University, 2014.
National Scholarship, Ministry of Education, China, 2011 and 2014.
HNA (HaiNan Airlines) Academic Excellence Scholarship, 2011.
First prize in National Undergraduate Electronic Design Contest, 2011.
First prize in National “Freescale Cup” Intelligent Car Competition, 2011.
Others
This is my previous CSDN blog in Chinese and it will not be updated. A new blog has been created recently.
My inspirations of research and life come from two Claudes: Claude Shannon and Claude Monet