Infinite-dimensional Log-Determinant divergences II: Alpha-Beta divergences

10/13/2016
by   Minh Ha Quang, et al.
0

This work presents a parametrized family of divergences, namely Alpha-Beta Log- Determinant (Log-Det) divergences, between positive definite unitized trace class operators on a Hilbert space. This is a generalization of the Alpha-Beta Log-Determinant divergences between symmetric, positive definite matrices to the infinite-dimensional setting. The family of Alpha-Beta Log-Det divergences is highly general and contains many divergences as special cases, including the recently formulated infinite dimensional affine-invariant Riemannian distance and the infinite-dimensional Alpha Log-Det divergences between positive definite unitized trace class operators. In particular, it includes a parametrized family of metrics between positive definite trace class operators, with the affine-invariant Riemannian distance and the square root of the symmetric Stein divergence being special cases. For the Alpha-Beta Log-Det divergences between covariance operators on a Reproducing Kernel Hilbert Space (RKHS), we obtain closed form formulas via the corresponding Gram matrices.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/26/2021

Estimation of Riemannian distances between covariance operators and Gaussian processes

In this work we study two Riemannian distances between infinite-dimensio...
research
08/25/2019

Riemannian Geometry of Symmetric Positive Definite Matrices via Cholesky Decomposition

We present a new Riemannian metric, termed Log-Cholesky metric, on the m...
research
07/16/2021

The strong converse exponent of discriminating infinite-dimensional quantum states

The sandwiched Rényi divergences of two finite-dimensional density opera...
research
09/29/2016

Kernel Methods on Approximate Infinite-Dimensional Covariance Operators for Image Classification

This paper presents a novel framework for visual object recognition usin...
research
08/05/2017

Learning Discriminative Alpha-Beta-divergence for Positive Definite Matrices (Extended Version)

Symmetric positive definite (SPD) matrices are useful for capturing seco...
research
04/13/2021

Learning Log-Determinant Divergences for Positive Definite Matrices

Representations in the form of Symmetric Positive Definite (SPD) matrice...

Please sign up or login with your details

Forgot password? Click here to reset