I'm an assistant professor in Department of Technology, Operations, and Statistics at Stern School of Business, New York University. I'm also affiliated faculty at NYU Center for Data Science. Before joining NYU Stern, I obtained my Ph.D. from Department of Electrical Engineering at Stanford University in summer 2019, advised by Professor Nick Bambos and Professor Peter Glynn. During the year 2019-2020, I was gratefully supported by the IBM Goldstine fellowship and also a visiting assistant professor at NYU Stern. My research interests lie at the intersection of machine learning, sequential decision making, optimization and stochastic systems. I'm broadly interested in developing sample-efficient and computationally efficient policy learning algorithms for data-driven decision making problems. Some of my recent research projects include distributionally robust policy learning, learning to adaptively bid in first-price auctions, efficient policy learning with limited adaptation, multi-agent cooperative and game-theoretical learning, offline policy learning using adaptively collected data. Email : zzhou@stern.nyu.edu

Recent News

1. 02/2022, If you are a PhD student in Ukraine working on related fields and would like to visit, please feel free to email me. Will try to help to the extent possible.

2. 09/2021, Our paper Distributionally Robust Batch Contextual Bandits was selected as a finalist for 2021 MSOM Best Student Paper Award

3. 09/2021, Our paper Simple Agent, Complex Environment: Efficient Reinforcement Learning with Agent State was selected as a finalist for 2021 INFORMS George Nicholson Best Student Paper Award

4. 08/2021, Our paper Dynamic Batch Learning in High-Dimensional Sparse Linear Contextual Bandits was selected as a finalist for 2021 INFORMS Service Science Section Best Paper Award.

5. 08/2021, Received a $450K grant from NSF (Award 2106508) Thank you, NSF!

6. 08/2021, Received Horizon Robotics faculty research award ($50,000). Thank you, Horizon Robotics!

7. 07/2021, Received JP Morgan AI Research grant ($10,000). Thank you, JP Morgan!

Recent Work

Below are some of my recent work (unpublished preprints):

1. Dynamic Batch Learning in High-Dimensional Sparse Linear Contextual Bandits
   Zhimei Ren and Zhengyuan Zhou

2. Optimal No-regret Learning in Repeated First-price Auctions
   Yanjun Han, Zhengyuan Zhou and Tsachy Weissman

3. Learning to Bid Optimally and Efficiently in Adversarial First-price Auctions
   Yanjun Han, Zhengyuan Zhou, Aaron Flores, Erik Ordentlich, Tsachy Weissman

4. Simple Agent, Complex Environment: Efficient Reinforcement Learning with Agent State
   Shi Dong, Ben Van Roy and Zhengyuan Zhou

5. Distributionally Robust Batch Contextual Bandits
   Nian Si, Fan Zhang, Zhengyuan Zhou and Jose Blanchet

6. Optimal No-Regret Learning in Strongly Monotone Games with Bandit Feedback
   Tianyi Lin, Zhengyuan Zhou, Wenjia Ba and Jiawei Zhang

Research Interests

• Contextual bandits

• Reinforcement learning

• Stochastic optimization

• Game-theoretical learning

• Revenue management

• Supply chains

• Recommendation systems

• Data-driven decision making