Any K\"ahler metric is a Fisher information metric
Emmanuel Gnandi

TL;DR
This paper demonstrates that all K"ahler metrics can be viewed as Fisher information metrics, establishing a statistical interpretation of K"ahler and co-K"ahler manifolds and linking geometric structures with information theory.
Contribution
It provides a novel characterization of K"ahler and co-K"ahler manifolds as Fisher information metrics, connecting complex geometry with statistical models.
Findings
K"ahler and co-K"ahler manifolds can be seen as parametric probability families.
Every real analytic K"ahler metric is locally a Fisher information metric.
Links between K"ahler potential and Kullback-Leibler divergence are established.
Abstract
The Fisher information metric or the Fisher-Rao metric corresponds to a natural Riemannian metric defined on a parameterized family of probability density functions. As in the case of Riemannian geometry, we can define a distance in terms of the Fisher information metric, called the Fisher-Rao distance. The Fisher information metric has a wide range of applications in estimation and information theories. Indeed, it provides the most informative Cramer-Rao bound for an unbiased estimator. The Goldberg conjecture is a well-known unsolved problem which states that any compact Einstein almost K\"ahler manifold is necessarily a K\"ahler-Einstein. Note that, there is also a known odd-dimensional analog of the Goldberg conjecture in the literature. The main objective of this paper is to establish a new characterization of coK\"ahler manifolds and K\"ahler manifolds; our characterization is…
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
TopicsStatistical Mechanics and Entropy
