Journal article icon

Journal article

Hamiltonian Variational Auto-Encoder

Abstract:

Variational Auto-Encoders (VAEs) have become very popular techniques to perform inference and learning in latent variable models as they allow us to leverage the rich representational power of neural networks to obtain flexible approximations of the posterior of latent variables as well as tight evidence lower bounds (ELBOs). Combined with stochastic variational inference, this provides a methodology scaling to large datasets. However, for this methodology to be practically efficient, it is n...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed
Version:
Accepted Manuscript

Actions


Access Document


Files:

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Statistics
More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Statistics
More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Statistics
Oxford college:
Mansfield College
ORCID:
0000-0001-5547-9213
Publisher:
Massachusetts Institute of Technology Press Publisher's website
Journal:
Advances in Neural Information Processing Systems Journal website
Volume:
31
Publication date:
2019
Acceptance date:
2018-09-05
ISSN:
1049-5258
Pubs id:
pubs:866279
URN:
uri:353d868e-af18-466c-94bb-76238febcf01
UUID:
uuid:353d868e-af18-466c-94bb-76238febcf01
Local pid:
pubs:866279
Keywords:

Terms of use


Metrics



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

TO TOP