Isometric Invariant Quantification of Gaussian Divergence over Poincare Disc
For information theory researchers, this offers a novel geometric perspective on Gaussian divergence, but the contribution is theoretical and incremental.
The paper establishes a geometric duality between the spherical squared-Hellinger distance and a hyperbolic isometric invariant, proposing the use of this invariant to quantify divergence between Gaussian measures. No concrete numerical results are provided.
The paper presents a 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 divergence between Gaussian measures as a contribution to information theory.