Entropic optimal transport is maximum-likelihood deconvolution
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...
Main Authors: | Rigollet, Philippe, Weed, Jonathan |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Mathematics |
Format: | Article |
Language: | English |
Published: |
Elsevier BV
2020
|
Online Access: | https://hdl.handle.net/1721.1/126692 |
Similar Items
-
Uncoupled isotonic regression via minimum Wasserstein deconvolution
by: Rigollet, Philippe, et al.
Published: (2020) -
Statistical bounds for entropic optimal transport: sample complexity and the central limit theorem
by: Mena, G, et al.
Published: (2019) -
Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration
by: Altschuler, Jason Max, et al.
Published: (2018) -
Estimation of Wasserstein distances in the Spiked Transport Model
by: Niles-Weed, Jonathan, et al.
Published: (2022) -
Efficient Marginal Likelihood Optimization in Blind Deconvolution
by: Levin, Anat, et al.
Published: (2011)