Show simple item record

dc.contributor.author
Jazbec, Metod
dc.contributor.author
Fortuin, Vincent
dc.contributor.author
Pearce, Michael
dc.contributor.author
Mandt, Stephan
dc.contributor.author
Rätsch, Gunnar
dc.date.accessioned
2021-01-22T15:30:01Z
dc.date.available
2021-01-22T11:38:50Z
dc.date.available
2021-01-22T15:30:01Z
dc.date.issued
2020-10-26
dc.identifier.uri
http://hdl.handle.net/20.500.11850/464741
dc.description.abstract
Conventional variational autoencoders fail in modeling correlations between data points due to their use of factorized priors. Amortized Gaussian process inference through GP-VAEs has led to significant improvements in this regard, but is still inhibited by the intrinsic complexity of exact GP inference. We improve the scalability of these methods through principled sparse inference approaches. We propose a new scalable GP-VAE model that outperforms existing approaches in terms of runtime and memory footprint, is easy to implement, and allows for joint end-to-end optimization of all components.
en_US
dc.language.iso
en
en_US
dc.publisher
Cornell University
en_US
dc.title
Scalable Gaussian Process Variational Autoencoders
en_US
dc.type
Working Paper
ethz.journal.title
arXiv
ethz.pages.start
2010.13472
en_US
ethz.size
24 p.
en_US
ethz.identifier.arxiv
2010.13472
ethz.publication.place
Ithaca, NY
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02150 - Dep. Informatik / Dep. of Computer Science::02661 - Institut für Maschinelles Lernen / Institute for Machine Learning::09568 - Rätsch, Gunnar / Rätsch, Gunnar
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02150 - Dep. Informatik / Dep. of Computer Science::02661 - Institut für Maschinelles Lernen / Institute for Machine Learning::09568 - Rätsch, Gunnar / Rätsch, Gunnar
ethz.relation.isPreviousVersionOf
handle/20.500.11850/501691
ethz.date.deposited
2021-01-22T11:39:04Z
ethz.source
BATCH
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2021-01-22T15:30:09Z
ethz.rosetta.lastUpdated
2022-03-29T04:56:24Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Scalable%20Gaussian%20Process%20Variational%20Autoencoders&rft.jtitle=arXiv&rft.date=2020-10-26&rft.spage=2010.13472&rft.au=Jazbec,%20Metod&Fortuin,%20Vincent&Pearce,%20Michael&Mandt,%20Stephan&R%C3%A4tsch,%20Gunnar&rft.genre=preprint&
 Search print copy at ETH Library

Files in this item

FilesSizeFormatOpen in viewer

There are no files associated with this item.

Publication type

Show simple item record