Zijian Liu

Email: zl3067 at stern dot nyu dot edu

[Google Scholar][CV]

About Me

I am currently a Ph.D. candidate majoring in Operations Management in the Department of Technology, Operations, and Statistics at the Leonard N. Stern School of Business, New York University. My advisor is Zhengyuan Zhou.

I am on the 2026-27 industry job market and seeking a full-time position! If you believe there's a potential fit, feel free to reach out.

Experience

Thomas J. Watson Research Center, IBM Research, May 2026 - Aug. 2026
Research Internship

Research Interests

Optimization, Sampling, Theoretical Machine Learning

Research Work

* indicates equal contribution, \(^\dagger\) indicates alphabetical order

Publications

  1. In-Expectation Convergence of Stochastic Gradient Methods under Heavy-Tailed Noise
    Zijian Liu
    In Proceedings of the 40th Annual Conference on Neural Information Processing Systems (NeurIPS 2026) (To Appear)
    [arXiv]
  2. On the Last-Iterate Convergence of Clipped Gradient Methods
    Zijian Liu
    In Proceedings of the 40th Annual Conference on Neural Information Processing Systems (NeurIPS 2026) (To Appear)
    [Available upon Request]
  3. Random Reshuffling Dominates Stochastic Gradient Descent
    Zijian Liu
    In Proceedings of the 39th Annual Conference on Learning Theory (COLT 2026)
    [arXiv][Proceedings][Extended version available below]
  4. Can Adaptive Gradient Methods Converge under Heavy-Tailed Noise? A Case Study of AdaGrad
    Zijian Liu
    In Proceedings of the 43rd International Conference on Machine Learning (ICML 2026)
    [arXiv][OpenReview]
  5. Clipped Gradient Methods for Nonsmooth Convex Optimization under Heavy-Tailed Noise: A Refined Analysis
    Zijian Liu
    In the 14th International Conference on Learning Representations (ICLR 2026)
    [arXiv (Full Version)][OpenReview][Proceedings]
  6. Online Convex Optimization with Heavy Tails: Old Algorithms, New Regrets, and Applications
    Zijian Liu
    In Proceedings of the 37th International Conference on Algorithmic Learning Theory (ALT 2026)
    [arXiv (Full Version)][OpenReview][Proceedings]
  7. Improved Last-Iterate Convergence of Shuffling Gradient Methods for Nonsmooth Convex Optimization
    Zijian Liu, Zhengyuan Zhou
    In Proceedings of the 42nd International Conference on Machine Learning (ICML 2025)
    [arXiv][OpenReview][Proceedings]
  8. Nonconvex Stochastic Optimization under Heavy-Tailed Noises: Optimal Convergence without Gradient Clipping
    Zijian Liu, Zhengyuan Zhou
    In the 13th International Conference on Learning Representations (ICLR 2025)
    [arXiv][OpenReview][Proceedings]
  9. On the Last-Iterate Convergence of Shuffling Gradient Methods
    Zijian Liu, Zhengyuan Zhou
    In Proceedings of the 41st International Conference on Machine Learning (ICML 2024) (Oral Presentation)
    [arXiv][OpenReview][Proceedings]
  10. On the Convergence of Projected Bures-Wasserstein Gradient Descent under Euclidean Strong Convexity
    Junyi Fan*, Yuxuan Han*, Zijian Liu, Jian-Feng Cai, Yang Wang, Zhengyuan Zhou
    In Proceedings of the 41st International Conference on Machine Learning (ICML 2024)
    [OpenReview][Proceedings]
  11. Revisiting the Last-Iterate Convergence of Stochastic Gradient Methods
    Zijian Liu, Zhengyuan Zhou
    In the 12th International Conference on Learning Representations (ICLR 2024)
    [arXiv (Full Version)][OpenReview][Proceedings]
  12. Breaking the Lower Bound with (Little) Structure: Acceleration in Non-Convex Stochastic Optimization with Heavy-Tailed Noise
    Zijian Liu, Jiawei Zhang, Zhengyuan Zhou
    In Proceedings of the 36th Annual Conference on Learning Theory (COLT 2023)
    [arXiv][Proceedings]
  13. High Probability Convergence of Stochastic Gradient Methods
    Zijian Liu*, Ta Duy Nguyen*, Thien Hang Nguyen*, Alina Ene, Huy L. Nguyen
    In Proceedings of the 40th International Conference on Machine Learning (ICML 2023)
    [arXiv (Full Version)][OpenReview][Proceedings]
  14. On the Convergence of AdaGrad(Norm) on \(\mathbb{R}^{d}\): Beyond Convexity, Non-Asymptotic Rate and Acceleration
    Zijian Liu*, Ta Duy Nguyen*, Alina Ene, Huy L. Nguyen
    In the 11th International Conference on Learning Representations (ICLR 2023)
    [arXiv][OpenReview]
  15. Adaptive Accelerated (Extra-)Gradient Methods with Variance Reduction
    Zijian Liu*, Ta Duy Nguyen*, Alina Ene, Huy L. Nguyen
    In Proceedings of the 39th International Conference on Machine Learning (ICML 2022)
    [arXiv][Proceedings]
  16. Distributionally Robust \(Q\)-Learning
    Zijian Liu, Qinxun Bai, Jose Blanchet, Perry Dong, Wei Xu, Zhengqing Zhou, Zhengyuan Zhou
    In Proceedings of the 39th International Conference on Machine Learning (ICML 2022)
    [Proceedings]

Manuscripts

  1. Product Return as a Sequence of Search Processes: Optimality and Search Duration
    Xiaoyu Fan\(^\dagger\), Srikanth Jagabathula\(^\dagger\), Zijian Liu\(^\dagger\), Eitan Muller\(^\dagger\)
    Major Revision at Operations Reseaerch, 2025
    [Available upon Request]
  2. Random Reshuffling for Smooth Convex Optimization: Dominates Stochastic Gradient Descent
    Zijian Liu
    In Submission, 2026
    [Optimization Online][Extended version of the COLT 2026 paper]
  3. Improved Analysis of Stein Variational Gradient Descent
    Zijian Liu, Soumyadip Ghosh, Yingdong Lu, Tomasz Nowicki
    In Submission, 2026
    [Available upon Request]
  4. Adam Converges in Nonsmooth Nonconvex Optimization
    Zijian Liu
    In Submission, 2026
    [arXiv]
  5. Near-Optimal Non-Convex Stochastic Optimization under Generalized Smoothness
    Zijian Liu, Srikanth Jagabathula, Zhengyuan Zhou
    Preprint, 2023
    [arXiv]
  6. Stochastic Nonsmooth Convex Optimization with Heavy-Tailed Noises: High-Probability Bound, In-Expectation Rate and Initial Distance Adaptation
    Zijian Liu, Zhengyuan Zhou
    Preprint, 2023
    [arXiv]
  7. META-STORM: Generalized Fully-Adaptive Variance Reduced SGD for Unbounded Functions
    Zijian Liu*, Ta Duy Nguyen*, Thien Hang Nguyen*, Alina Ene, Huy L. Nguyen
    Preprint, 2022
    [arXiv]