Conference item icon

Conference item

Auto-encoding sequential Monte Carlo

Abstract:
We build on auto-encoding sequential Monte Carlo (AESMC): a method for model and proposal learning based on maximizing the lower bound to the log marginal likelihood in a broad family of structured probabilistic models. Our approach relies on the efficiency of sequential Monte Carlo (SMC) for performing inference in structured probabilistic models and the flexibility of deep neural networks to model complex conditional probability distributions. We develop additional theoretical insights and introduce a new training procedure which improves both model and proposal learning. We demonstrate that our approach provides a fast, easy-to-implement and scalable means for simultaneous model learning and proposal adaptation in deep generative models.
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:
OpenReview
Host title:
Sixth International Conference on Learning Representations (ICLR), Vancouver Canada, 30th April - 3rd May, 2018
Journal:
International Conference on Learning Representations (ICLR) More from this journal
Publication date:
2018-02-15
Acceptance date:
2018-01-29


Pubs id:
pubs:959092
UUID:
uuid:3c35d146-4402-40d4-ae1c-1e1c3d09b17a
Local pid:
pubs:959092
Deposit date:
2019-01-11
ARK identifier:

Terms of use


Views and Downloads

Views and downloads will return soon






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

TO TOP