Conference item
Filtering variational objectives
- Abstract:
-
When used as a surrogate objective for maximum likelihood estimation in latent variable models, the evidence lower bound (ELBO) produces state-of-the-art results. Inspired by this, we consider the extension of the ELBO to a family of lower bounds defined by a particle filter’s estimator of the marginal likelihood, the filtering variational objectives (FIVOs). FIVOs take the same arguments as the ELBO, but can exploit a model’s sequential structure to form tighter bounds. We present...
Expand abstract
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Authors
Bibliographic Details
- Publisher:
- Neural Information Processing Systems Foundation
- Host title:
- Advances in Neural Information Processing Systems
- Journal:
- Advances in Neural Information Processing Systems More from this journal
- Volume:
- 30
- Publication date:
- 2017-12-07
- Acceptance date:
- 2017-09-07
- ISSN:
-
1049-5258
Item Description
- Pubs id:
-
pubs:727812
- UUID:
-
uuid:66c9958e-aa4d-4eab-96af-a2dc147893cf
- Local pid:
-
pubs:727812
- Source identifiers:
-
727812
- Deposit date:
-
2017-09-12
Terms of use
- Copyright holder:
- Neural Information Processing Systems Foundation
- Copyright date:
- 2017
- Notes:
-
This is the author accepted manuscript following peer review version of the article. The final version is
available online from Neural Information Processing Systems Foundation at: https://papers.nips.cc/paper/7235-filtering-variational-objectives
Metrics
If you are the owner of this record, you can report an update to it here: Report update to this record