Conference item icon

Conference item

Learning latent permutations with Gumbel-Sinkhorn networks

Abstract:

Permutations and matchings are core building blocks in a variety of latent variable models, as they allow us to align, canonicalize, and sort data. Learning in such models is difficult, however, because exact marginalization over these combinatorial objects is intractable. In response, this paper introduces a collection of new methods for end-to-end learning in such models that approximate discrete maximum-weight matching using the continuous Sinkhorn operator. Sinkhorn iteration is attracti...

Expand abstract
Publication status:
Published
Peer review status:
Reviewed (other)

Actions


Access Document


Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Statistics
Role:
Author
ORCID:
0000-0003-4432-9679
Publisher:
OpenReview
Journal:
ICLR 2018 Conference Track More from this journal
Volume:
2018
Pages:
1-22
Publication date:
2018-05-01
Acceptance date:
2017-11-20
Event title:
6th International Conference on Learning Representations
Language:
English
Keywords:
Pubs id:
1136150
Local pid:
pubs:1136150
Deposit date:
2020-10-05

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP