Ziwei Guan 

Ziwei is a Research Scientist at Meta Platform, Inc., working inside the Modern Recommendation System Org. He was a PhD student at THE Ohio State University, advised by Prof. Yingbin Liang. And he successfully defended his thesis on Dec 2023. During the past five years (2018-2023), he has studied the bandit algorithms, reinforcement learning, bilevel optimization, and online optimization. He has also gained experience with the modern computer vision and natural language processing technique during his internships as an AI Scientist at SAP. And he also engaged with the team of group recommendation at Meta in Summer 2022 as a SWE intern. 

Education 

The Ohio State University

•  Aug. 2018 -  Dec. 2023

•  PhD in Electrical and Computer Engineering

•  Advisor: Prof. Yingbin Liang,  her website

University of Science and Technology of China 

• Sept. 2014 - Jul. 2018

• Bachelor of Engineering, Majoring in Electrical and Electronic Informatic Engineering

Experience

Meta 

• Research Scientist

• Jan 2024 - present

SAP 

• AI Scientist Intern

• May 2023 - Oct 2023

Meta 

• Software Engineer Intern

• May  2022 - Aug 2022

Publications

• On the Hardness of Online Nonconvex Optimization with Single Oracle Feedback 

Guan, Z., Zhou, Y., Liang, Y. 2024, ICLR 2024

• Faster Algorithm and Sharper Analysis for Constrained Markov Decision Process 

   Li, T.;  Guan, Z.;  Zou, S.; Xu, T.; Liang, Y.; Lan, G., Operation Research Letters 2024

• Online Nonconvex Optimization with Limited Instantaneous Oracle Feedback 

Guan, Z., Zhou, Y., Liang, Y. 2023, COLT 2023

• PER-ETD: A Polynomially Efficient Emphatic Temporal Difference Learning Method 

Guan, Z.; Xu, T. and Liang, Y. 2022,  ICLR 2022. 

• When Will Generative Adversarial Imitation Learning Algorithms Attain Global Convergence 

     Guan, Z.; Xu, T. and Liang, Y. 2021, AIStats 2021

• Robust Dynamic Spectrum Access in Adversarial Environments 

Guan, Z.; Hu, T.Y.; Ji, K.; Bucci Jr, D.J.; Palombo, J.; Liston, M. and Liang, Y., 2020. IEE ICC, 2020

• Robust Stochastic Bandit Algorithms under Probabilistic Unbounded Adversarial Attack

Guan, Z.; Ji, K.; Bucci Jr, D.J.; Hu, T.Y.; Palombo, J.; Liston, M. and Liang, Y., 2020. AAAI  2020.   

Pre-prints

• A Constrained Optimization Approach to Bilevel Optimization with Multiple Inner Minima

Sow, D; Guan, Z; Ji, K, Liang,Y; arXiv pre-print