Log-determinant divergences revisited: alpha-beta and gamma log-det divergences
From MaRDI portal
Publication:296329
DOI10.3390/E17052988zbMATH Open1338.94034DBLPjournals/entropy/CichockiCA15arXiv1412.7146OpenAlexW2963959237WikidataQ60486507 ScholiaQ60486507MaRDI QIDQ296329FDOQ296329
Authors: Andrzej Cichocki, Sergio Cruces, Shun-Ichi Amari
Publication date: 15 June 2016
Published in: Entropy (Search for Journal in Brave)
Abstract: In this paper, we review and extend a family of log-det divergences for symmetric positive definite (SPD) matrices and discuss their fundamental properties. We show how to generate from parameterized Alpha-Beta (AB) and Gamma Log-det divergences many well known divergences, for example, the Stein's loss, S-divergence, called also Jensen-Bregman LogDet (JBLD) divergence, the Logdet Zero (Bhattacharryya) divergence, Affine Invariant Riemannian Metric (AIRM) as well as some new divergences. Moreover, we establish links and correspondences among many log-det divergences and display them on alpha-beta plain for various set of parameters. Furthermore, this paper bridges these divergences and shows also their links to divergences of multivariate and multiway Gaussian distributions. Closed form formulas are derived for gamma divergences of two multivariate Gaussian densities including as special cases the Kullback-Leibler, Bhattacharryya, R'enyi and Cauchy-Schwartz divergences. Symmetrized versions of the log-det divergences are also discussed and reviewed. A class of divergences is extended to multiway divergences for separable covariance (precision) matrices.
Full work available at URL: https://arxiv.org/abs/1412.7146
Cites Work
- Maximum likelihood estimation for the tensor normal distribution: Algorithm, minimum sample size, and empirical bias and dispersion
- Separable covariance arrays via the Tucker product, with applications to multivariate relational data
- Array variate random variables with multiway Kronecker delta covariance matrix structure
- The multilinear normal distribution: introduction and some basic properties
- Majorization, doubly stochastic matrices, and comparison of eigenvalues
- Hilbert's projective metric in quantum information theory
- Robust parameter estimation with a small bias against heavy contamination
- Positive definite matrices
- Divergence Function, Duality, and Convex Analysis
- Families of alpha-, beta- and gamma-divergences: flexible and robust measures of similarities
- Entropy differential metric, distance and divergence measures in probability spaces: A unified approach
- Optimal shrinkage of eigenvalues in the spiked covariance model
- Means of Hermitian positive-definite matrices based on the log-determinant \(\alpha\)-divergence function
- Positive definite matrices and the S-divergence
- $\alpha$-Divergence Is Unique, Belonging to Both $f$-Divergence and Bregman Divergence Classes
- Optimal Shrinkage of Singular Values
- Jensen divergence-based means of SPD matrices
- Factorizations of invertible density matrices
Cited In (12)
- Some notes on quantum Hellinger divergences with Heinz means
- Nonnegative Matrix Factorization and Log-Determinant Divergences
- Geometry-aware principal component analysis for symmetric positive definite matrices
- Entropic regularization of Wasserstein distance between infinite-dimensional Gaussian measures and Gaussian processes
- Averaging symmetric positive-definite matrices
- Infinite-dimensional log-determinant divergences between positive definite Hilbert-Schmidt operators
- Quantum divergences with \(p\)-power means
- Alpha-beta log-determinant divergences between positive definite trace class operators
- Least informative distributions in maximum \(q\)-log-likelihood estimation
- Entropy-regularized 2-Wasserstein distance between Gaussian measures
- Alpha Procrustes metrics between positive definite operators: a unifying formulation for the Bures-Wasserstein and Log-Euclidean/Log-Hilbert-Schmidt metrics
- Title not available (Why is that?)
This page was built for publication: Log-determinant divergences revisited: alpha-beta and gamma log-det divergences
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q296329)