The Hessian transport gradient flows and sampling methods
组织者
演讲者
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?