Publications

You can also find my articles on my Google Scholar profile.

Simulation of Wasserstein geometric flows from a generative approach


A parameterized Wasserstein Hamiltonian flow approach for solving the Schrödinger equation

Hao Wu, Shu Liu, Xiaojing Ye, Haomin Zhou

arXiv: 2505.11762

Parameterized Wasserstein gradient flow

Yijie Jin, Shu Liu, Hao Wu, Xiaojing Ye, Haomin Zhou

Journal of Computational Physics Volume 524, 2025

Numerical Analysis on Neural Network projected schemes for approximating one dimensional Wasserstein Gradient Flows

Xinzhe Zuo, Jiaxi Zhao, Shu Liu, Stanley Osher, Wuchen Li

Journal of Computational Physics (JCP), Volume 546, 1 February 2026

Parametrized Wasserstein Hamiltonian flow

Hao Wu, Shu Liu, Xiaojing Ye, Haomin Zhou

SIAM Journal on Numerical Analysis, Vol. 63, Iss. 1 pp.360-395, 2025.

Neural parametric Fokker-Planck equations

Shu Liu, Wuchen Li, Hongyuan Zha, Haomin Zhou

SIAM Journal on Numerical Analysis, Vol. 60, Iss. 3, pp. 1385-1449, 2022

Primal-Dual algorithm for numerical PDEs with preconditioning


A Natural Primal-Dual Hybrid Gradient Method for Adversarial Neural Network Training on Solving Partial Differential Equations

Shu Liu, Stanley Osher, Wuchen Li

arXiv: 2411.06278. 2024

A first-order computational method for Reaction-Diffusion type equations via Primal-Dual Hybrid Gradient method

Shu Liu, Siting Liu, Stanley Osher, Wuchen Li

Journal of Computational Physics (JCP), Volume 500, 2024.

Numerical analysis of a first-order computational algorithm for reaction-diffusion equations via the primal-dual hybrid gradient method

Shu Liu, Xinzhe Zuo, Stanley Osher, Wuchen Li

Mathematics of Computation (Math. Comp.), July 11, 2025.

Computational methods related to optimal transport & Hamilton-Jacobi equation


Neural Hamilton-Jacobi Characteristic Flows for Optimal Transport

Yesom Park, Shu Liu, Mo Zhou, Stanley Osher

arXiv: 2510.01153, Accepted by the 14th International Conference on Learning Representations (ICLR), 2026

A supervised learning scheme for computing Hamilton-Jacobi equation via density coupling

Jianbo Cui, Shu Liu, Haomin Zhou

SIAM Journal on Scientific Computing Vol.48, Iss. 1 pp C51–C76, 2026.

Neural Monge Map estimation and its applications.

Jiaojiao Fan∗, Shu Liu∗, Shaojun Ma, Haomin Zhou, Yongxin Chen

Transaction on Machine Learning Research (TMLR) Featured Certification, 2023

A particle-evolving method for approximating the optimal transport plan

Shu Liu∗, Haodong Sun∗, Hongyuan Zha

Geometric Science of Information, 2021

Learning high dimensional Wasserstein geodesics

Shu Liu∗, Shaojun Ma∗, Yongxin Chen, Hongyuan Zha, Haomin Zhou

arXiv:2102.02992. 2021

Control & Sampling on discrete sets


Accelerated Markov Chain Monte Carlo Algorithms on Discrete States

Bohan Zhou, Shu Liu, Xinzhe Zuo, Wuchen Li

arXiv: 2505.12599

Optimal Control for Stochastic Nonlinear Schrödinger Equation on Graph

Jianbo Cui, Shu Liu, Haomin Zhou

SIAM Journal on Control and Optimization Vol. 61, Iss. 4 2023.

Wasserstein Hamiltonian flow with common noise on graph.

Jianbo Cui, Shu Liu, Haomin Zhou

SIAM Journal on Applied Mathematics, Vol. 83, Iss. 2 pp. 484 - 509, 2023.

Stochastic Wasserstein Hamiltonian Flows.

Jianbo Cui, Shu Liu, Haomin Zhou

Journal of Dynamics and Differential Equations, Volume 36, pages 3885–3921, 2024.

What is a stochastic Hamiltonian process on finite graph? An optimal transport answer

Jianbo Cui, Shu Liu, Haomin Zhou

Journal of Differential Equations (JDE), Vol. 305, Pages 428-457, 2021

Other publications


Learning stochastic behaviour from aggregate data.

Shaojun Ma, Shu Liu, Hongyuan Zha, Haomin Zhou

Proceedings of the 38th International Conference on Machine Learning (ICML), 2021