|
Scientific Part
Mathematics
Wasserstein and weighted metrics for multidimensional Gaussian distributions
M. Y. Kelberta, Y. Suhovb a Higher School of Economics — National Research University, 20
Myasnitskaya St., Moscow 101000, Russia
b DPMMS, Penn State University, 201 Old Main, State College, PA 16802, USA
Abstract:
We present a number of low and upper bounds for Lévy – Prokhorov, Wasserstein, Frechét, and Hellinger distances between probability distributions of the same or different dimensions. The weighted (or context-sensitive) total variance and Hellinger distances are introduced. The upper and low bounds for these weighted metrics are proved. The low bounds for the minimum of different errors in sensitive hypothesis testing are proved.
Key words:
Lévy – Prokhorov distance, Wasserstein distance, weighted total variance distance, Dobrushin's inequality, weighted Pinsker's inequality, weighted le Cam's inequality, weighted Fano's inequality.
Received: 09.12.2022 Accepted: 25.12.2022
Citation:
M. Y. Kelbert, Y. Suhov, “Wasserstein and weighted metrics for multidimensional Gaussian distributions”, Izv. Saratov Univ. Math. Mech. Inform., 23:4 (2023), 422–434
Linking options:
https://www.mathnet.ru/eng/isu993 https://www.mathnet.ru/eng/isu/v23/i4/p422
|
Statistics & downloads: |
Abstract page: | 74 | Full-text PDF : | 26 | References: | 14 |
|