Zeyu Zheng

Assistant Professor 

University of California, Berkeley

Office: 4125 Etcheverry Hall

Education Background

Ph.D. in Management Science and Engineering, Stanford University, 2018

M.A. in Economics, Stanford University, 2016

B.S. in Mathematics, Peking University, 2012

Research

      • Stochastic simulation

      • Non-stationary stochastic modeling

Publication

      • Dynamic Pricing with External Information and Inventory Constraint, with Xiaocheng Li, accepted by Management Science, 2023

      • Gradient-based Simulation Optimization Algorithms via Multi-Resolution System Approximations, with Jingxu Xu, accepted by INFORMS Journal on Computing, 2023.

      • Learning to Simulate Sequentially Generated Data via Neural Networks and Wasserstein Training, with Tingyu Zhu and Haoyu Liu, accepted by ACM Transactions on Modeling and Computer Simulation (TOMACS), 2023.

      • Combining Numerical Linear Algebra with Simulation to Compute Stationary Distributions, with Alex Infanger and Peter W. Glynn, Proceedings of the Winter Simulation Conference, 2022.

      • A Simple and Optimal Policy Design with Safety against Heavy-tailed Risk for Multi-armed Bandits, with Feng Zhu and David Simchi-Levi, Conference on Neural Information Processing Systems (NeurIPS), 2022.  

      • Gradient-Free Methods for Deterministic and Stochastic Nonsmooth Nonconvex Optimization, with Tianyi Lin and Michael I. Jordan, Conference on Neural Information Processing Systems (NeurIPS), 2022.

      • Bounding Stationary Expectations for Queues and Storage Processes Fed by Stationary Input Sequences, with Peter W. Glynn, Queueing Models and Service Management, 2022.

      • Non-stationary A/B Tests, with Yuhang Wu, Guangyu Zhang, Zuohua Zhang and Chu Wang, ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'22), research track, 2022. 

      • Inference on the Best Policies with Many Covariates, with Waverly Wei, Yuqing Zhou and Jingshen Wang, accepted by Journal of Econometrics, 2022

      • Gradient-based Algorithms for Convex Discrete Optimization via Simulation, with Haixiang Zhang and Javad Lavaei, accepted by Operations Research, 2022.

      • Immediacy Provision and Matchmaking, with Yu An, accepted by Management Science, 2022

      • Stochastic L-Convex Function Minimization, with Haixiang Zhang and Javad Lavaei, Conference on Neural Information Processing Systems (NeurIPS), 2021.  

      • Scalable Graphene Defect Prediction using Transferable Learning, with Bowen Zheng and Grace X. Gu, Nanomaterials, 2021.  

      • Dynamic Planning and Learning under Recovering Rewards, with Feng Zhu and David Simchi-Levi, International Conference on Machine Learning (ICML) 2021.  

      • Learning to Simulate Sequentially Generated Data via Neural Networks and Wasserstein Training, with Tingyu Zhu, Proceedings of the Winter Simulation Conference (WSC) 2021.

      • Efficient Computation for Stratified Splitting, with Peter W. Glynn, Proceedings of the Winter Simulation Conference (WSC) 2021.

      • On Projection Robust Optimal Transport: Sample Complexity and Model Misspecification, with Tianyi Lin, Elynn Y. Chen, Marco Cuturi, and Michael I. Jordan, International Conference on Artificial Intelligence and Statistics (AISTATS) 2021.

      • When Demands Evolve Larger and Noisier: Learning and Earning in a Growing Environment, with Feng Zhu, International Conference on Machine Learning (ICML) 2020.  

      • Joint Resource Allocation for Input Data Collection and Simulation, with Jingxu Xu and Peter W. Glynn, Proceedings of the Winter Simulation Conference (WSC) 2020.  

      • Simulating Nonstationary Spatio-Temporal Poisson Processes using Inversion Method, with Haoting Zhang, Proceedings of the Winter Simulation Conference (WSC) 2020.

      • Approximating Systems Fed by Poisson Processes with Rapidly Changing Arrival Rates, with Harsha Honnappa and Peter W. Glynn, 2020, Operations Research

      • Method of Moments Estimation for Lévy-driven Ornstein-Uhlenbeck Stochastic Volatility Models, with Xiangyu Yang, Yanfang Wu, Jian-Qiang Hu, 2020, Probability in the Engineering and Informational Sciences

      • Estimation and Inference for Non-stationary Arrival Models, with Peter W. Glynn, 2019, Proceedings of the Winter Simulation Conference.

      • Rates of Convergence and CLTs for Subcanonical Debiased MLMC, with Jose Blanchet and Peter W. Glynn, 2018, Monte Carlo and Quasi-Monte Carlo Methods, Springer Proceedings in Mathematics & Statistics, vol 241, pp 465-479. 

      • Data-driven Ranking and Selection with High Dimensional Covariates and General Dependence, with Xiaocheng Li and Xiaowei Zhang, 2018, Proceedings of the Winter Simulation Conference.

      • Fitting Continuous Piecewise Linear Poisson Intensities via Maximum Likelihood and Least Squares, with Peter W. Glynn, 2017, Proceedings of the Winter Simulation Conference

      • A CLT for Infinitely Stratified Estimators, with Applications to Debiased MLMC, with Peter W. Glynn, ESAIM: Proceedings and Surveys (B. Bouchard, E. Gobet and B. Jourdain, Editors), vol 59, pp 104-114. 

      • Extensions of the Regenerative Method to New Functionals, with Peter W. Glynn, 2016, Proceedings of the Winter Simulation Conference


Working Paper

      • Best Arm Identification with Fairness Constraints on Subpopulations, with Yuhang Wu and Tingyu Zhu.

      • Adaptive A/B Tests and Simultaneous Treatment Parameter Optimization, with Yuhang Wu, Guangyu Zhang, Zuohua Zhang and Chu Wang.

      • A Simple and Optimal Policy Design with Safety against Heavy-tailed Risk for Stochastic Bandits, with Feng Zhu and David Simchi-Levi; preliminary version appeared in NeurIPS 2022.  

      • Non-stationary A/B Tests: Optimal Variance Reduction, Bias Correction, and Valid Inference, with Yuhang Wu, Guangyu Zhang, Zuohua Zhang and Chu Wang; preliminary version appeared in KDD 2022. 

      • Selecting the Best Optimizing System, with Nian Si.

      • Offline Planning and Online Learning under Recovering Rewards, with Feng Zhu and David Simchi-Levi; preliminary version appeared in ICML 2021.

      • Approximating Performance Measures for Slowly Changing Non-stationary Markov Chains, with Harsha Honnappa and Peter W. Glynn. 

Teaching/Courses

Spring 2019, INDENG 173, Introduction to Stochastic Processes.

Fall 2019, INDENG 263A, Applied Stochastic Processes I.

Spring 2020, INDENG 173, Introduction to Stochastic Processes.

Spring 2020, INDENG 174, Simulation for Enterprise-scale Systems.

Spring 2021, INDENG 173, Introduction to Stochastic Processes.

Fall 2021, INDENG 263A, Applied Stochastic Processes I.

Spring 2022, INDENG 173, Introduction to Stochastic Processes.












.