Conference item
Fast computation of Wasserstein barycenters
- Abstract:
-
We present new algorithms to compute the mean of a set of N empirical probability measures under the optimal transport metric. This mean, known as the Wasserstein barycenter \citepagueh2011barycenters,rabin2012, is the measure that minimizes the sum of its Wasserstein distances to each element in that set. We argue through a simple example that Wasserstein barycenters have appealing properties that differentiate them from other barycenters proposed recently, which all build on kernel smoothin...
Expand abstract
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Authors
Bibliographic Details
- Publisher:
- Journal of Machine Learning Research Publisher's website
- Host title:
- Proceedings of Machine Learning Research
- Journal:
- Proceedings of Machine Learning Research Journal website
- Volume:
- 32
- Issue:
- 2
- Pages:
- 685-693
- Publication date:
- 2014-06-21
- Acceptance date:
- 2014-04-09
- Event location:
- Beijing, China
- EISSN:
-
1533-7928
- ISSN:
-
1532-4435
Item Description
- Keywords:
- Pubs id:
-
pubs:502924
- UUID:
-
uuid:176f66e9-3fef-4847-b638-ace71b630ec5
- Local pid:
- pubs:502924
- Source identifiers:
-
502924
- Deposit date:
- 2019-08-16
Terms of use
- Copyright holder:
- Cuturi, M and Doucet, A
- Copyright date:
- 2014
- Notes:
- © The Author(s) 2014. This paper was presented at the 31st International Conference on Machine Learning, 22-24 June 2014, Bejing, China. The final published version is available online from Proceedings of Machine Learning Research at: http://proceedings.mlr.press/v32/cuturi14.html
Metrics
If you are the owner of this record, you can report an update to it here: Report update to this record