Yuliang Wang

Contact

Office: 372 Science Building No. 6, Shanghai Jiao Tong University, 800 Dongchuan Road, Shanghai, 200240, P.R.China.

Email: yuliangwang_math AT sjtu DOT edu DOT cn

Research interest

My research interest lies in applied math, including stochastic algorithms (for sampling, machine learning and particle systems etc), minmax optimization, diffusion models, sequential Monte Carlo, etc.

Publications

(in alphabetical order)

1. Uniform-in-time error estimate of random batch method with replacement for the Cucker-Smale model
   Yuelin Wang, Yuliang Wang
   arxiv preprint | https://arxiv.org/abs/2501.15152

2. On Random Batch Methods (RBM) for interacting particle systems driven by L\'evy processes
   Jian-Guo Liu, Yuliang Wang
   arxiv preprint | https://arxiv.org/abs/2412.06291

3. Error estimates of the Euler's method for stochastic differential equations with multiplicative noise via relative entropy
   Lei Li, Mengchao Wang, Yuliang Wang
   arxiv preprint | https://arxiv.org/abs/2409.04991

4. Guidance for twisted particle filter: a continuous-time perspective
   Jianfeng Lu, Yuliang Wang
   arxiv preprint | https://arxiv.org/abs/2409.02399

5. Convergence of Random Batch Method with replacement for interacting particle systems
   Zhenhao Cai, Jian-Guo Liu, Yuliang Wang
   arxiv preprint | https://arxiv.org/abs/2407.19315

6. Propagation of chaos in path spaces via information theory
   Lei Li, Yuelin Wang, Yuliang Wang
   arxiv preprint | https://arxiv.org/abs/2312.00339

7. Geometric ergodicity of SGLD via reflection coupling
   Lei Li, Jian-Guo Liu, Yuliang Wang
   arxiv preprint | https://arxiv.org/abs/2301.06769

8. A sharp uniform-in-time error estimate for Stochastic Gradient Langevin Dynamics
   Lei Li, Yuliang Wang
   arxiv preprint | https://arxiv.org/abs/2207.09304

9. On uniform-in-time diffusion approximation for stochastic gradient descent
   Lei Li, Yuliang Wang
   arxiv preprint | https://arxiv.org/abs/2207.04922

10. Topic-aware chatbot using Recurrent Neural Networks and Nonnegative Matrix Factorization
    Yuchen Guo, Nicholas Hanoian, Zhexiao Lin, Nicholas Liskij, Hanbaek Lyu, Deanna Needell, Jiahao Qu, Henry Sojico, Yuliang Wang, Zhe Xiong, Zhenhong Zou
    arxiv preprint | https://arxiv.org/abs/1912.00315

Education and experience

2020.9-present. Math. Ph.D. candidate. Shanghai Jiao Tong Univeristy. (advised by Prof. Lei Li)

2024.3-present. Visit scholar. Duke University. (advised by Prof. Jianfeng Lu)

2016.9-2020.6. Math and applied math (Zhiyuan Honors Program). B.S. Shanghai Jiao Tong Univeristy.(thesis advised by Prof. Lei Li)

2019.6-2020.1. Visit scholar. University of California, Los Angeles. (advised by Prof. Deanna Needell and Prof. Hanbaek Lyu)

2018.6-2018.7. Exchange. Hertford College, Oxford University.

Talks

Past talks:

1. On the ergodicity and sharp error estimate of Stochastic Gradient Langevin Dynamics
   2022.12 | AMPHD seminar , Fudan University, Shanghai

2. Ergodicity and sharp error estimate of Stochastic Gradient Langevin Dynamics
   2023.8 | ICIAM2023, Tokyo

3. Random Batch Methods and Kinetic Monte Carlo for Interacting Particle Systems with Levy Noise
   2025.2 | Zu Chongzhi Mathematics Research Seminar, Duke-Kunshan University, Kunshan

Teaching

Malliavin calculus, Yuliang Wang, Shanghai Jiao Tong University, Spring 2022 - Fall 2023 (lecturer).

Artificial intelligence and partial differential equations, Lei Li, Harbin, Summer 2023 (TA).

MA378, Optimization, Lei Li, Shanghai Jiao Tong University, Fall 2023 (TA).

MA1208, Calculus, Gang Zhou, Shanghai Jiao Tong University, Fall 2022 (TA).

MA378, Optimization, Lei Li, Shanghai Jiao Tong University, Fall 2021 (TA).

MA1608H, Mathematical analysis, Kaizhi Wang, Shanghai Jiao Tong University, Fall 2020 (TA).