Zhengyu Zhou

Office address

Dartmouth College

Hanover, NH, USA

I am a Research Associate at Dartmouth College, where I am working with Prof. Yaoqing Yang. My current research interests lie broadly in machine learning theory and optimization, with a focus on matrix optimization, random matrix theory, model diagnosis, and loss landscape geometry.

Before joining Dartmouth, I completed my Ph.D. study in the School of Computer Science at Wuhan University, advised by Prof. Weiwei Liu. I received my B.S. degree in Mathematics from Wuhan University in 2021.

I am interested in understanding the geometry, dynamics, and reliability of modern machine learning models, especially through tools from matrix analysis, random matrix theory, and model diagnosis.

I am particularly interested in the following topics:

Matrix optimization and spectral methods
Random matrix theory in machine learning
Model diagnosis and model comparison
Loss landscape geometry
Optimization and generalization in deep learning

Academic Service

Conference Reviewer: ICML, NeurIPS, AISTATS, ICLR

Journal Reviewer: JMLR, IEEE TPAMI, Biometrika

I review for JMLR

news

Jul 1, 2026	I joined the Department of Computer Science at Dartmouth College as a postdoctoral researcher in July 2026.
Jun 1, 2026	I received my Ph.D. in Computer Science in June 2026.
Sep 25, 2024	Our co-first-authored work with Xin Zou, “A Boosting-Type Convergence Result for AdaBoost.MH with Factorized Multi-Class Classifiers,” resolved an open problem posed at COLT 2014 and was published at NeurIPS 2024.

latest posts

selected publications

JMLR

Sample Complexity for Distributionally Robust Learning under chi-square divergence

Zhengyu Zhou, and Weiwei Liu

Journal of Machine Learning Research, 2023

Bib PDF

@article{JMLR:v24:22-0881,
  author = {Zhou, Zhengyu and Liu, Weiwei},
  title = {Sample Complexity for Distributionally Robust Learning under chi-square divergence},
  journal = {Journal of Machine Learning Research},
  year = {2023},
  volume = {24},
  number = {230},
  pages = {1--27},
}

ICML

An Error Analysis of Flow Matching for Deep Generative Modeling

Spotlight

Zhengyu Zhou, and Weiwei Liu

In Proceedings of the 42nd International Conference on Machine Learning, 2025

Bib PDF

@inproceedings{zhou2025error,
  title = {An Error Analysis of Flow Matching for Deep Generative Modeling},
  author = {Zhou, Zhengyu and Liu, Weiwei},
  booktitle = {Proceedings of the 42nd International Conference on Machine Learning},
  series = {Proceedings of Machine Learning Research},
  volume = {267},
  pages = {78903--78932},
  year = {2025},
  publisher = {PMLR},
}

AAAI

Rademacher Complexity for Distributionally Robust Learning

Oral

Zhengyu Zhou, and Weiwei Liu

In Proceedings of the AAAI Conference on Artificial Intelligence, 2026

Bib PDF

@inproceedings{zhou2026rademacher,
  title = {Rademacher Complexity for Distributionally Robust Learning},
  author = {Zhou, Zhengyu and Liu, Weiwei},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
  volume = {40},
  number = {34},
  pages = {29098--29106},
  year = {2026},
  doi = {10.1609/aaai.v40i34.40147},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/40147},
}

ICML

Sequential Kernel Goodness-of-fit Testing

Zhengyu Zhou, and Weiwei Liu

In Proceedings of the 41st International Conference on Machine Learning, 2024

Bib PDF

@inproceedings{zhou2024sequential,
  title = {Sequential Kernel Goodness-of-fit Testing},
  author = {Zhou, Zhengyu and Liu, Weiwei},
  booktitle = {Proceedings of the 41st International Conference on Machine Learning},
  series = {Proceedings of Machine Learning Research},
  volume = {235},
  pages = {62057--62075},
  year = {2024},
  publisher = {PMLR},
}

AAAI

On the Robustness of Bandit Multiple Testing

Zhengyu Zhou, and Weiwei Liu

In Proceedings of the AAAI Conference on Artificial Intelligence, 2026

Bib PDF

@inproceedings{zhou2026robustness,
  title = {On the Robustness of Bandit Multiple Testing},
  author = {Zhou, Zhengyu and Liu, Weiwei},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
  volume = {40},
  number = {34},
  pages = {29107--29114},
  year = {2026},
  doi = {10.1609/aaai.v40i34.40148},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/40148},
}