Zhengqing Zhou   周正清

About me I am currrently working as a quantitative researcher at Susquehanna International Group. I received my PhD in Mathematics from Stanford (2021), advised by Prof. Peter Glynn, Prof. Jose Blanchet, and Prof. George Papanicolaou (co-advise). I was a member in Advanced Financial Technologies Laboratory (AFTLab). Prior to Stanford, I obtained my bachelor's degree in School of Mathematical Science from USTC (2016). Contact Email: zqzhou [at] stanford [dot] edu LinkedIn Google Scholar

Research Interests

• Algorithmic Trading

• Applied Probability

• Distributionally Robust Optimization

• Statistical Machine Learning

Research

• Sequential Batch Learning in Finite-Action Linear Contextual Bandits
  Yanjun Han, Zhengqing Zhou, Zhengyuan Zhou, Jose H. Blanchet, Peter W. Glynn, Yinyu Ye

• Unbiased Optimal Stopping via the MUSE
  Zhengqing Zhou†, Guanyang Wang†, Jose H. Blanchet, Peter W. Glynn

• Distributionally Robust Martingale Optimal Transport
  Zhengqing Zhou, Jose H. Blanchet, Peter W. Glynn

• Multivariate Distributionally Robust Convex Regression under Absolute Error Loss
  Jose H. Blanchet, Peter W. Glynn, Jun Yan, Zhengqing Zhou^*
  Conference on Neural Information Processing Systems (NeurIPS), 2019
  [Slides] [Poster] [Code]

• Batched Multi-armed Bandits Problem
  Zijun Gao, Yanjun Han, Zhimei Ren, Zhengqing Zhou^*
  Conference on Neural Information Processing Systems (NeurIPS)(Oral), 2019
  [Slides] [Poster] [Code]

• Finite-Sample Regret Bound for Distributionally Robust Offline Tabular Reinforcement Learning
  Zhengqing Zhou, Zhengyuan Zhou, Qinxun Bai, Linhai Qiu, Jose H. Blanchet, Peter W. Glynn
  International Conference on Artificial Intelligence and Statistics (AISTATS), 2021

• Optimal Communication Rates for Zero-Error Distributed Simulation under Blackboard Communication Protocols
  Yanjun Han, Kedar Tatwawadi, Gowtham Kurri, Zhengqing Zhou, Vinod Prabhakaran, Tsachy Weissman
  IEEE Transactions on Information Theory (to appear), 2021

Talks

• Distributionally Robust Martingale Optimal Transport
  

  AFTLab Doctoral Conference, June 2019, Stanford, CA

• Distributionally Robust Convex Regression
  

  INFORMS Annual Meeting, October 2019, Seattle, WA

• Distributionally Robust Offline Reinforcement Learning
  

  INFORMS Annual Meeting, November 2020, Online

Professional Activities

• Journal reviewing: Mathematics of Operations Reserach, Advances in Applied Probability, Latin American Journal of Probability and Mathematical Statistics, Journal of the American Statistical Association.

• Conference reviewing: NeurIPS 2019 Workshop on Information Theory and Machine Learning, NeurIPS 2020-2022, ICLR 2021-2022, ICML 2021.