数学科学研究所
Insitute of Mathematical Science

Seminar: Scalable physics-informed deep generative models for solving forward and inverse stochastic differential equations

Seminar| Institute of Mathematical Sciences

Time: Friday, January 16th, 2026,15:00-16:00

LocationIMS, RS408

Speaker: Ling Guo, Shanghai Normal University


Abstract: Physics-informed deep learning approaches have been developed to solve forward and inverse stochastic differential equation (SDE) problems with high-dimensional stochastic space. However, the existing deep learning models have difficulties solving SDEs in the high-dimensional spatial space. In this talk, we will present a scalable physics-informed deep generative model (sPI-GeM), which is capable of solving SDE problems with both high-dimensional stochastic and spatial space. A series of numerical experiments, including approximation of Gaussian and non-Gaussian stochastic processes, forward and inverse SDE problems, are performed to demonstrate the accuracy of the proposed model.


地址:上海市浦东新区华夏中路393号
邮编:201210
上海市徐汇区岳阳路319号8号楼
200031(岳阳路校区)