EUVIMEDEUVIMED entdecken
Crossref

Regularized Divergences Between Covariance Operators and Gaussian Measures on Hilbert Spaces

Hà Quang Minh

Journal of Theoretical Probability · 2021-06 · 34 (2) · 580-643

DOI: 10.1007/s10959-020-01003-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Theoretical Probability, online erschienen am 25.03.2020. Verfasst von Hà Quang Minh. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 36 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This work presents an infinite-dimensional generalization of the correspondence between the Kullback-Leibler and Renyi divergences between Gaussian measures on Euclidean space and the Alpha Log-Determinant divergences between symmetric, positive definite matrices. Specifically, we present the regularized Kullback-Leibler and Renyi divergences between covariance operators and Gaussian measures on an infinite-dimensional Hilbert space, which are defined using the infinite-dimensional Alpha Log-Determinant divergences between positive definite trace class operators. We show that, as the regularization parameter approaches zero, the regularized Kullback-Leibler and Renyi divergences between two equivalent Gaussian measures on a Hilbert space converge to the corresponding true divergences. The explicit formulas for the divergences involved are presented in the most general Gaussian setting.

Zitieren

APA

Minh, H. Q. (2021). Regularized Divergences Between Covariance Operators and Gaussian Measures on Hilbert Spaces. Journal of Theoretical Probability, 34(2), 580-643. https://doi.org/10.1007/s10959-020-01003-2

Vancouver

Minh HQ. Regularized Divergences Between Covariance Operators and Gaussian Measures on Hilbert Spaces. Journal of Theoretical Probability. 2021;34(2):580-643. doi:10.1007/s10959-020-01003-2

BibTeX
@article{Minh2021,
  author = {Minh, Hà Quang},
  title = {Regularized Divergences Between Covariance Operators and Gaussian Measures on Hilbert Spaces},
  journal = {Journal of Theoretical Probability},
  year = {2021},
  volume = {34},
  number = {2},
  pages = {580--643},
  doi = {10.1007/s10959-020-01003-2}
}
Kostenlos starten →