Laplacian operator on statistical manifold
Ruichao Jiang, Javad Tavakoli, Yiqiang Zhao

TL;DR
This paper introduces a novel Laplacian operator on statistical manifolds, called the vector Laplacian, which integrates the Amari-Chentsov tensor and has applications in heat kernel analysis.
Contribution
It defines the vector Laplacian on statistical manifolds and derives a formula, extending geometric analysis tools to information geometry.
Findings
Derived a formula for the vector Laplacian.
Presented two applications involving the heat kernel.
Enhanced understanding of geometric structures in statistical manifolds.
Abstract
In this paper, we define a Laplacian operator on a statistical manifold, called the vector Laplacian. This vector Laplacian incorporates information from the Amari-Chentsov tensor. We derive a formula for the vector Laplacian. We also give two applications using the heat kernel associated with the vector Laplacian.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGeometric Analysis and Curvature Flows · Tensor decomposition and applications
