Logarithmic divergences: geometry and interpretation of curvature

06/17/2019
by   Ting-Kam Leonard Wong, et al.
0

We study the logarithmic L^(α)-divergence which extrapolates the Bregman divergence and corresponds to solutions to novel optimal transport problems. We show that this logarithmic divergence is equivalent to a conformal transformation of the Bregman divergence, and, via an explicit affine immersion, is equivalent to Kurose's geometric divergence. In particular, the L^(α)-divergence is a canonical divergence of a statistical manifold with constant sectional curvature -α. For such a manifold, we give a geometric interpretation of its sectional curvature in terms of how the divergence between a pair of primal and dual geodesics differ from the dually flat case. Further results can be found in our follow-up paper [27] which uncovers a novel relation between optimal transport and information geometry.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/31/2019

Optimal transport and information geometry

Optimal transport and information geometry are both mathematical framewo...
research
12/10/2017

Logarithmic divergences from optimal transport and Rényi geometry

Divergences, also known as contrast functions, are distance-like quantit...
research
01/18/2019

Gambling and Rényi Divergence

For gambling on horses, a one-parameter family of utility functions is p...
research
11/24/2018

Divergence Prior and Vessel-tree Reconstruction

We propose a new geometric regularization principle for reconstructing v...
research
05/08/2021

Projections with logarithmic divergences

In information geometry, generalized exponential families and statistica...
research
07/19/2023

Geometry in global coordinates in mechanics and optimal transport

For a manifold embedded in an inner product space, we express geometric ...
research
05/11/2023

Generalized Iterative Scaling for Regularized Optimal Transport with Affine Constraints: Application Examples

We demonstrate the relevance of an algorithm called generalized iterativ...

Please sign up or login with your details

Forgot password? Click here to reset