June 8 (Sat), 2019 10:05--11:05, 14:00--15:00 Lecture Hall (Room No. 420) Research Institute for Mathematical Sciences Kyoto University, Kyoto, Japan |
Abstract
Information geometry has emerged from a study on invariant structure of a family of probability distributions.
The invariance gives a second-order symmetric tensor $g$ and a third order-symmetric tensor $T$ as unique invariant quantities.
A pair $(g, T)$ defines a Riemannian metric and dual affine connections which together preserves the metric.
Information geometry studies a Riemannian manifold having a pair of dual affine connections.
Such a structure also arises from an asymmetric divergence function and affine differential geometry.
In particular, a dually flat Riemannian manifold is important for applications, because a generalized
Pythagorean theorem and projection theorem hold. Wasserstein distance gives another important geometry
which is non-invariant, preserving the metric of a sample space. We try to construct information geometry
of the entropy-regularized Wasserstein distance.