BIMSA >
BIMSA Computational Math Seminar
Learning Generalized Diffusions using an Energetic Variational Approach
Learning Generalized Diffusions using an Energetic Variational Approach
演讲者
卢裕滨
时间
2025年11月13日 15:30 至 16:30
地点
A3-4-312
线上
Zoom 928 682 9093
(BIMSA)
摘要
Extracting governing physical laws from computational or experimental data is crucial across various fields such as fluid dynamics and plasma physics. Many of those physical laws are dissipative due to fluid viscosity or plasma collisions. In this talk, we introduce a framework for learning these governing laws by leveraging the system's energy-dissipation laws, assuming either continuous data (probability density) or discrete data (particles) are available. Our methods offer several key advantages, including their robustness to corrupted/noisy observations, their easy extension to more complex physical systems, and the potential to address higher-dimensional systems. We validate our approaches through representative numerical examples and carefully investigate the impacts of data quantity and data property on model discovery.
演讲者介绍
Yubin Lu is a Senior Research Associate at the Illinois Institute of Technology. He received his B.S. in 2017 and Ph.D. in 2022, both in the school of Mathematics and Statistics from the Huazhong University of Science and Technology. His research focuses on data-driven modeling, stochastic dynamical systems, and generative models.