Entropic optimal transport is maximum-likelihood deconvolution

Author(s)
Rigollet, Philippe; Weed, Jonathan
Thumbnail
DownloadSubmitted version (163.2Kb)
Terms of use
Creative Commons Attribution-NonCommercial-NoDerivs License http://creativecommons.org/licenses/by-nc-nd/4.0/
Metadata
Show full item record
Abstract
We give a statistical interpretation of entropic optimal transport by showing that performing maximum-likelihood estimation for Gaussian deconvolution corresponds to calculating a projection with respect to the entropic optimal transport distance. This structural result gives theoretical support for the wide adoption of these tools in the machine learning community.
Date issued
2018-11
URI
https://hdl.handle.net/1721.1/126692
Department
Massachusetts Institute of Technology. Department of Mathematics
Journal
Comptes Rendus Mathematique
Publisher
Elsevier BV
Citation
Rigollet, Philippe and Jonathan Weed. "Entropic optimal transport is maximum-likelihood deconvolution." Comptes Rendus Mathematique 356, 11-12 (November 2018): 1228-1235 © 2018 Académie des sciences
Version: Original manuscript
ISSN
1631-073X
Collections