Conference item
Reparameterizing the Birkhoff polytope for variational permutation inference
- Abstract:
-
Many matching, tracking, sorting, and ranking problems require probabilistic reasoning about possible permutations, a set that grows factorially with dimension. Combinatorial optimization algorithms may enable efficient point estimation, but fully Bayesian inference poses a severe challenge in this high-dimensional, discrete space. To surmount this challenge, we start by relaxing the discrete set of permutation matrices to its convex hull the Birkhoff polytope, the set of doubly-stochastic ma...
Expand abstract
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Preview, Version of record, 2.1MB, Terms of use)
-
- Publication website:
- http://proceedings.mlr.press/v84/linderman18a.html
Authors
Bibliographic Details
- Publisher:
- Proceedings of Machine Learning Research
- Journal:
- Proceedings of Machine Learning Research More from this journal
- Volume:
- 84
- Publication date:
- 2018-04-01
- Acceptance date:
- 2017-11-17
- Event title:
- International Conference on Artificial Intelligence and Statistics 2018
- Event location:
- Canary Islands
- Event start date:
- 2018-04-09
- Event end date:
- 2018-04-11
Item Description
- Language:
-
English
- Keywords:
- Pubs id:
-
1136148
- Local pid:
-
pubs:1136148
- Deposit date:
-
2020-10-05
Terms of use
- Copyright holder:
- Linderman et al.
- Copyright date:
- 2018
- Rights statement:
- Copyright 2018 by the author(s). This paper is available under a Creative Commons (CC-BY) licence.
- Notes:
- This paper was presented at the International Conference on Artificial Intelligence and Statistics 2018, Canary Islands, April 2018. The final version of this paper is available online from Proceedings of Machine Learning Research at: http://proceedings.mlr.press/v84/linderman18a.html
- Licence:
- CC Attribution (CC BY)
Metrics
If you are the owner of this record, you can report an update to it here: Report update to this record