Conference item icon

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


Access Document


Files:

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Statistics
Role:
Author
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
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


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