Regularized divergences between covariance operators and Gaussian measures on Hilbert spaces
DOI10.1007/s10959-020-01003-2zbMath1476.28015arXiv1904.05352OpenAlexW3013816997MaRDI QIDQ2031001
Publication date: 8 June 2021
Published in: Journal of Theoretical Probability (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1904.05352
Hilbert spaceKullback-Leibler divergenceGaussian measuresRényi divergencecovariance operatorsregularized divergences
Gaussian processes (60G15) Determinants, permanents, traces, other special matrix functions (15A15) Linear operators belonging to operator ideals (nuclear, (p)-summing, in the Schatten-von Neumann classes, etc.) (47B10) Positive linear operators and order-bounded operators (47B65) Set functions and measures and integrals in infinite-dimensional spaces (Wiener measure, Gaussian measure, etc.) (28C20)
Related Items
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- On Bayesian A- and D-optimal experimental designs in infinite dimensions
- Equivalence and perpendicularity of Gaussian processes
- Notes on infinite determinants of Hilbert space operators
- Log-determinant divergences between positive definite Hilbert-Schmidt operators
- Infinite-dimensional log-determinant divergences between positive definite trace class operators
- Infinite-dimensional log-determinant divergences between positive definite Hilbert-Schmidt operators
- Alpha-beta log-determinant divergences between positive definite trace class operators
- A unified formulation for the Bures-Wasserstein and log-Euclidean/log-Hilbert-Schmidt distances between positive definite operators
- Means of Hermitian positive-definite matrices based on the log-determinant \(\alpha\)-divergence function
- Nonpositive curvature: A geometrical approach to Hilbert-Schmidt operators
- An introduction to infinite-dimensional analysis
- Equivalence and Radon-Nikodym derivatives of Gaussian measures
- On operator ranges
- A Riemannian framework for tensor computing
- Affine-Invariant Riemannian Distance Between Infinite-Dimensional Covariance Operators
- Inverse problems: A Bayesian perspective
- On a property of normal distributions of any stochastic process
- Kullback--Leibler Approximation for Probability Measures on Infinite Dimensional Spaces
- Algorithms for Kullback--Leibler Approximation of Probability Measures in Infinite Dimensions
- Covariances in Computer Vision and Machine Learning
- Geometric Means in a Novel Vector Space Structure on Symmetric Positive‐Definite Matrices
- Randon-Nikodym Derivatives of Stationary Gaussian Measures
- Radon-Nikodym Derivatives of Gaussian Measures