Mo ZhouSchool of Mathematical Sciences, Peking University
中文 / English

Research

My research lies at the intersection of control theory, machine learning, and artificial intelligence. I develop efficient algorithms and rigorous theoretical foundations for stochastic optimal control, mean field control, and mean field games. I am also interested in reinforcement learning, normalizing flows, and generative models.

Publications

Corresponding author

Preprints

  1. Self-supervised In-context Operator Learning for Stochastic Mean-Field Control

    Suyi Gao, Mo Zhou, Rongjie Lai

    arXiv preprint arXiv:2608.18282 (2026).

    arXiv

  2. Learning Mean-Field Games through Mean-Field Actor-Critic Flow

    Mo Zhou, Haosheng Zhou, Ruimeng Hu

    arXiv preprint arXiv:2510.12180 (2025).

    arXiv

  3. Variational Conditional Normalizing Flows for Computing Second-order Mean Field Control Problems

    Jiaxi Zhao, Mo Zhou, Xinzhe Zuo, Wuchen Li

    arXiv preprint arXiv:2503.19580 (2025).

    arXiv

  4. Solving Time-Continuous Stochastic Optimal Control Problems: Algorithm Design and Convergence Analysis of Actor-Critic Flow

    Mo Zhou, Jianfeng Lu

    arXiv preprint arXiv:2402.17208 (2024).

    arXiv

Published and Accepted Papers

  1. Neural Hamilton-Jacobi Characteristic Flows for Optimal Transport

    Yesom Park, Shu Liu, Mo Zhou, Stanley Osher*

    The Fourteenth International Conference on Learning Representations (ICLR 2026).

    OpenReviewarXiv

  2. Simulating Fokker-Planck Equations via Mean Field Control of Score-based Normalizing Flows

    Mo Zhou*, Stanley Osher, Wuchen Li

    Journal of Computational Physics 566 (2026): 115274.

    JournalDOIarXiv

  3. Score-based Neural Ordinary Differential Equations for Computing Mean Field Control Problems

    Mo Zhou*, Stanley Osher, Wuchen Li*

    Journal of Computational Physics (2025): 114369.

    JournalarXiv

  4. A Deep Learning Algorithm for Computing Mean Field Control Problems via Forward-Backward Score Dynamics

    Mo Zhou, Stanley Osher, Wuchen Li*

    Research in the Mathematical Sciences 12.3 (2025): 42.

    JournalarXiv

  5. A Policy Gradient Framework for Stochastic Optimal Control Problems with Global Convergence Guarantee

    Mo Zhou*, Jianfeng Lu

    SIAM Journal on Control and Optimization 63.4 (2025): 2605-2631.

    JournalarXiv

  6. A Neural Network Warm-Start Approach for the Inverse Acoustic Obstacle Scattering Problem

    Mo Zhou, Jiequn Han*, Manas Rachh, Carlos Borges

    Journal of Computational Physics 490 (2023): 112341.

    JournalarXiv

  7. Single Time-scale Actor-critic Method to Solve the Linear Quadratic Regulator with Convergence Guarantees

    Mo Zhou*, Jianfeng Lu

    Journal of Machine Learning Research 24.222 (2023): 1-34.

    PaperarXiv

  8. Actor-Critic Method for High Dimensional Static Hamilton--Jacobi--Bellman Partial Differential Equations Based on Neural Networks

    Mo Zhou, Jiequn Han*, Jianfeng Lu

    SIAM Journal on Scientific Computing 43.6 (2021): A4043-A4066.

    JournalarXiv

  9. Solving High-dimensional Eigenvalue Problems Using Deep Neural Networks: A Diffusion Monte Carlo Like Approach

    Jiequn Han*, Jianfeng Lu, Mo Zhou

    Journal of Computational Physics 423 (2020): 109792.

    JournalarXiv

Ph.D. Thesis

  1. Deep Learning Method for Partial Differential Equations and Optimal Problems

    Mo Zhou

    Ph.D. thesis, Duke University (2023).

    Thesis