| dc.contributor |
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
|
| dc.contributor |
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
|
| dc.creator |
Alvarez Melis, David |
|
| dc.creator |
Jegelka, Stefanie Sabrina |
|
| dc.creator |
Jaakkola, Tommi S |
|
| dc.date |
2021-01-11T17:20:16Z |
|
| dc.date |
2021-01-11T17:20:16Z |
|
| dc.date |
2019-02 |
|
| dc.date |
2018-06 |
|
| dc.date |
2020-12-21T16:34:35Z |
|
| dc.date.accessioned |
2023-03-01T08:02:47Z |
|
| dc.date.available |
2023-03-01T08:02:47Z |
|
| dc.identifier |
2640-3498 |
|
| dc.identifier |
https://hdl.handle.net/1721.1/129368 |
|
| dc.identifier |
Alvarez-Melis, David, Stefanie Jegelka and Tommi S. Jaakkola. “Towards optimal transport with global invariances.” Proceedings of Machine Learning Research PMLR, 89 (February 2019): 1870-1879 © 2019 The Author(s) |
|
| dc.identifier.uri |
http://localhost:8080/xmlui/handle/CUHPOERS/275954 |
|
| dc.description |
Many problems in machine learning involve calculating correspondences between sets of objects, such as point clouds or images. Discrete optimal transport provides a natural and successful approach to such tasks whenever the two sets of objects can be represented in the same space, or at least distances between them can be directly evaluated. Unfortunately neither requirement is likely to hold when object representations are learned from data. Indeed, automatically derived representations such as word embeddings are typically fixed only up to some global transformations, for example, reflection or rotation. As a result, pairwise distances across two such instances are ill-defined without specifying their relative transformation. In this work, we propose a general framework for optimal transport in the presence of latent global transformations. We cast the problem as a joint optimization over transport couplings and transformations chosen from a flexible class of invariances, propose algorithms to solve it, and show promising results in various tasks, including a popular unsupervised word translation benchmark. |
|
| dc.description |
National Science Foundation (U.S.). Career Grant (Award 1553284) |
|
| dc.format |
application/pdf |
|
| dc.language |
en |
|
| dc.publisher |
JMLR |
|
| dc.relation |
http://proceedings.mlr.press/v89/ |
|
| dc.relation |
Proceedings of Machine Learning Research PMLR |
|
| dc.rights |
Creative Commons Attribution-Noncommercial-Share Alike |
|
| dc.rights |
http://creativecommons.org/licenses/by-nc-sa/4.0/ |
|
| dc.source |
arXiv |
|
| dc.title |
Towards optimal transport with global invariances |
|
| dc.type |
Article |
|
| dc.type |
http://purl.org/eprint/type/ConferencePaper |
|