paper-with-me

Papers

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

2016-10-13 · Minh Ha Quang

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.

📄 PDF Abstract BibTeX arXiv:1610.08087

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Kullback-Leibler and Renyi divergences in reproducing kernel Hilbert space and Gaussian process settings

2022-07-18 · Minh Ha Quang

In this work, we present formulations for regularized Kullback-Leibler and R\'enyi divergences via the Alpha Log-Determinant (Log-Det) divergences between positive Hilbert-Schmidt operators on Hilbert spaces in two diffe…

Gaussian Processes

The alpha-beta divergence for real and complex data

2025-08-05 · Sergio Cruces arxiv

Divergences are fundamental to the information criteria that underpin most signal processing algorithms. The alpha-beta family of divergences, designed for non-negative data, offers a versatile framework that parameteriz…

Learning Log-Determinant Divergences for Positive Definite Matrices

2021-04-13 · Anoop Cherian, Panagiotis Stanitsas, Jue Wang, Mehrtash Harandi 외

Representations in the form of Symmetric Positive Definite (SPD) matrices have been popularized in a variety of visual learning applications due to their demonstrated ability to capture rich second-order statistics of vi…

ClusteringDictionary Learning

Learning the Information Divergence

2014-06-05 · Onur Dikmen, Zhirong Yang, Erkki Oja

Information divergence that measures the difference between two nonnegative matrices or tensors has found its use in a variety of machine learning problems. Examples are Nonnegative Matrix/Tensor Factorization, Stochasti…

BIG-bench Machine LearningTopic Models

Computing Divergences between Discrete Decomposable Models

2021-12-08 · Loong Kuan Lee, Nico Piatkowski, François Petitjean, Geoffrey I. Webb

There are many applications that benefit from computing the exact divergence between 2 discrete probability measures, including machine learning. Unfortunately, in the absence of any assumptions on the structure or indep…