The Hessian transport gradient flows and sampling methods
组织者
丘成栋
演讲者
康家熠
时间
2022年09月20日 16:30 至 17:00
地点
Online
线上
Tencent 735 7908 4302
()
摘要
It turns out that there are two geometric structures in the probability space related to the de Bruijn identity. One is Wasserstein geometry, which refers to the heat flows or Gaussian kernels. The other one is information geometry, which relates to the differential structures of the entropy. A natural question arises: What are natural families of geometries in the probability space that connect entropy/divergence functions, heat flows, and the de Bruijn identity?
演讲者介绍
Jiayi Kang received his Ph.D. in Mathematics from Tsinghua University in 2024. He joined the Beijing Institute of Mathematical Sciences and Applications (BIMSA) as an Assistant Researcher in July 2024, and became an Assistant Professor at the Hetao Institute for Mathematical and Interdisciplinary Sciences (HIMIS) in November 2025.
His research focuses on the intersection of deep learning, nonlinear filtering, and computational biology. His main research interests include: neural network-based filtering algorithms and their mathematical foundations, sampling methods in Wasserstein geometry, nonlinear filtering theory (including the Yau-Yau method) and its applications in climate science and other fields, as well as computational genomics and evolutionary system modeling. He is committed to solving complex problems in science and engineering using mathematical and machine learning methods.