|
|
|
|
| LEADER |
00911 am a22001693u 4500 |
| 001 |
126692 |
| 042 |
|
|
|a dc
|
| 100 |
1 |
0 |
|a Rigollet, Philippe
|e author
|
| 100 |
1 |
0 |
|a Massachusetts Institute of Technology. Department of Mathematics
|e contributor
|
| 700 |
1 |
0 |
|a Weed, Jonathan
|e author
|
| 245 |
0 |
0 |
|a Entropic optimal transport is maximum-likelihood deconvolution
|
| 260 |
|
|
|b Elsevier BV,
|c 2020-08-20T00:59:20Z.
|
| 856 |
|
|
|z Get fulltext
|u https://hdl.handle.net/1721.1/126692
|
| 520 |
|
|
|a 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.
|
| 546 |
|
|
|a en
|
| 655 |
7 |
|
|a Article
|
| 773 |
|
|
|t Comptes Rendus Mathematique
|
