arXiv:2602.17159 · v9

Isometric Invariant Quantification of Gaussian Divergence over Poincare Disc

Poincaré圆盘上高斯散度的等距不变量化

首次提交 2026-02-19 16:14

版本更新 2026-11-10 23:43

雷达观测 2026-11-11 13:07

摘要

The paper presents a statistical geometric duality between the spherical squared-Hellinger distance and a hyperbolic isometric invariant of the Poincare disc under the action of the general Mobius group. Motivated by the geometric connection, we propose the usage of the L2-embedded hyperbolic isometric invariant as an alternative way to quantify statistical divergence between Gaussian measures as a contribution to information theory and machine learning.