- Library Home /
- Search Collections /
- Open Collections /
- Browse Collections /
- BIRS Workshop Lecture Videos /
- Regularization of Barycenters in the Wasserstein Space
Open Collections
BIRS Workshop Lecture Videos
BIRS Workshop Lecture Videos
Regularization of Barycenters in the Wasserstein Space Cazelles, Elsa
Description
The concept of barycenter in the Wasserstein space corresponds to define a notion of Fréchet mean of a set of probability measures. However, depending on the data at hand, such barycenters may be irregular. We thus introduce a convex regularization of Wasserstein barycenters for random measures supported on $\mathbb{R}^d$. We prove the existence and uniqueness of such barycenters for a large class of regularizing functions. A stability result of regularized barycenters in terms of Bregman distance associated to the convex regularization term is also given. This allows to compare the case of data made of $n$ probability measures $\nu_1,\ldots,\nu_n$ with the more realistic setting where we have only access to a dataset of random variables $(X_{i,j})_{1\leq i\leq n; 1\leq j\leq p_i}$ organized in the form of $n$ experimental units such that $X_{i,1},\ldots,X_{i,p_i}$ are iid observations sampled from the measure $\nu_i$ for each $1\leq i\leq n$. We also analyse the convergence of the regularized empirical barycenter of a set o $n$ iid random probability measures towards its population counterpart, and we discuss its rate of convergence. This approach is shown to be appropriate for the statistical analysis of discrete or absolutely continuous random measures.
Item Metadata
Title |
Regularization of Barycenters in the Wasserstein Space
|
Creator | |
Publisher |
Banff International Research Station for Mathematical Innovation and Discovery
|
Date Issued |
2017-05-01T13:00
|
Description |
The concept of barycenter in the Wasserstein space corresponds to define a notion of Fréchet mean of a set of probability measures. However, depending on the data at hand, such barycenters may be irregular. We thus introduce a convex regularization of Wasserstein barycenters for random measures supported on $\mathbb{R}^d$. We prove the existence and uniqueness of such barycenters for a large class of regularizing functions. A stability result of regularized barycenters in terms of Bregman distance associated to the convex regularization term is also given. This allows to compare the case of data made of $n$ probability measures $\nu_1,\ldots,\nu_n$ with the more realistic setting where we have only access to a dataset of random variables $(X_{i,j})_{1\leq i\leq n; 1\leq j\leq p_i}$ organized in the form of $n$ experimental units such that $X_{i,1},\ldots,X_{i,p_i}$ are iid observations sampled from the measure $\nu_i$ for each $1\leq i\leq n$. We also analyse the convergence of the regularized empirical barycenter of a set o $n$ iid random probability measures towards its population counterpart, and we discuss its rate of convergence. This approach is shown to be appropriate for the statistical analysis of discrete or absolutely continuous random measures.
|
Extent |
20 minutes
|
Subject | |
Type | |
File Format |
video/mp4
|
Language |
eng
|
Notes |
Author affiliation: Institut de Mathématiques de Bordeaux
|
Series | |
Date Available |
2017-10-29
|
Provider |
Vancouver : University of British Columbia Library
|
Rights |
Attribution-NonCommercial-NoDerivatives 4.0 International
|
DOI |
10.14288/1.0357377
|
URI | |
Affiliation | |
Peer Review Status |
Unreviewed
|
Scholarly Level |
Graduate
|
Rights URI | |
Aggregated Source Repository |
DSpace
|
Item Media
Item Citations and Data
Rights
Attribution-NonCommercial-NoDerivatives 4.0 International