Junhui Zhang

Junhui Zhang

PhD Candidate in Operations Research at MIT

I am a 5th year PhD student at MIT Operations Research Center, and I am fortunate to be advised by Prof. Patrick Jaillet. I am broadly interested in optimization, with a focus on developing (communication, oracle, memory, etc.) efficient algorithms for large scale problems and for sequential decision making.

Previously, I graduated Summa Cum Laude from Columbia University in 2021 with a B.S. degree in Applied Math. Here is my CV.


Preprints

  • Multi-Timescale Gradient Sliding for Distributed Optimization.
    Junhui Zhang, Patrick Jaillet. Under review. link
    • Extended abstract accepted by the 39th Neural Information Processing Systems (NeurIPS) workshop OPT 2025: ”Statistics Meets Optimization”, 2025.
  • Efficient Online Mirror Descent Stochastic Approximation for Multi-Stage Stochastic Programming.
    Junhui Zhang, Patrick Jaillet. Work in progress. link
  • Secretary Problems with Random Number of Candidates: How Prior Distributional Information Helps.
    Junhui Zhang, Patrick Jaillet. Under review. link


Publications

  • Quadratic memory is necessary for optimal query complexity in convex optimization: Center-of-mass is pareto-optimal.
    Moïse Blanchard, Junhui Zhang, Patrick Jaillet. Mathematics of Operations Research, 2024. link
    • Previous version appeared at the 36th Annual Conference on Learning Theory (COLT), 2023.
  • Memory-Constrained Algorithms for Convex Optimization via Recursive Cutting-Planes.
    Moïse Blanchard, Junhui Zhang, Patrick Jaillet. 37th Neural Information Processing Systems (NeurIPS), 2023. link
  • Distributionally constrained black-box stochastic gradient estimation and optimization.
    Henry Lam, Junhui Zhang. Operations Research, 2024. link
    • Short version appeared at Winter Simulation Conference (WSC), 2020.
  • Square root principal component pursuit: tuning-free noisy robust matrix recovery.
    Junhui Zhang, Jingkai Yan, John Wright. 35th Neural Information Processing Systems (NeurIPS), 2021. link
  • Principal Component Pursuit for Pattern Identification in Environmental Mixtures.
    Elizabeth A Gibson, Junhui Zhang, Jingkai Yan, Lawrence Chillrud, Jaime Benavides, Yanelli Nunez, Julie B Herbstman, Jeff Goldsmith, John Wright, Marianthi-Anna Kioumourtzoglou. Environmental Health Perspectives, 2022. link


Teaching experience

  • TA for 6.7700 Fundamentals of Probability, Fall 2025, MIT
  • TA for 6.3700 Introduction to Probability, Spring 2024, MIT
  • TA for MATH 3028 Partial Differential Equation, Spring 2020, Columbia University
  • TA for MATH 4061 Modern Analysis I, Fall 2019, Columbia University


Awards

  • INFORMS Undergraduate Operations Research Prize finalist, INFORMS, 2021.
    • For the work Distributionally constrained black-box stochastic gradient estimation and optimization.
  • Applied Math Faculty Award, Applied Physics & Applied Mathematics Dept., Columbia University, 2021.


Services

Reviewer: AISTATS (2025), ALT (2024, 2025), NeurIPS (2024, 2025), ICLR (2025)


Last update: October 2025