How to Train Deep Variational Autoencoders and Probabilistic Ladder Networks

Casper Kaae Sønderby, Tapani Raiko, Lars Maaløe, Søren Kaae Sønderby, Ole Winther

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

14577 Downloads (Pure)

Abstract

Variational autoencoders are a powerful framework for unsupervised learning. However, previous work has been restricted to shallow models with one or two layers of fully factorized stochastic latent variables, limiting the flexibility of the latent representation. We propose three advances in training algorithms of variational autoencoders, for the first time allowing to train deep models of up to five stochastic layers, (1) using a structure similar to the Ladder network as the inference model, (2) warm-up period to support stochastic units staying active in early training, and (3) use of batch normalization. Using these improvements we show state-of-the-art log-likelihood results for generative modeling on several benchmark datasets.
Original languageEnglish
Title of host publicationProceedings of the 33rd International Conference on Machine Learning (ICML 2016)
Number of pages9
Publication date2016
Publication statusPublished - 2016
Event33rd International Conference on Machine Learning (ICML 2016) - New York, United States
Duration: 19 Jun 201624 Jun 2016
Conference number: 33
http://icml.cc/2016/

Conference

Conference33rd International Conference on Machine Learning (ICML 2016)
Number33
CountryUnited States
CityNew York
Period19/06/201624/06/2016
Internet address
SeriesJMLR: Workshop and Conference Proceedings
Volume48
ISSN1938-7228

Cite this

Sønderby, C. K., Raiko, T., Maaløe, L., Sønderby, S. K., & Winther, O. (2016). How to Train Deep Variational Autoencoders and Probabilistic Ladder Networks. In Proceedings of the 33rd International Conference on Machine Learning (ICML 2016) JMLR: Workshop and Conference Proceedings, Vol.. 48
Sønderby, Casper Kaae ; Raiko, Tapani ; Maaløe, Lars ; Sønderby, Søren Kaae ; Winther, Ole. / How to Train Deep Variational Autoencoders and Probabilistic Ladder Networks. Proceedings of the 33rd International Conference on Machine Learning (ICML 2016). 2016. (JMLR: Workshop and Conference Proceedings, Vol. 48).
@inproceedings{4ac1c67ae5a1439db82bda1c175dea94,
title = "How to Train Deep Variational Autoencoders and Probabilistic Ladder Networks",
abstract = "Variational autoencoders are a powerful framework for unsupervised learning. However, previous work has been restricted to shallow models with one or two layers of fully factorized stochastic latent variables, limiting the flexibility of the latent representation. We propose three advances in training algorithms of variational autoencoders, for the first time allowing to train deep models of up to five stochastic layers, (1) using a structure similar to the Ladder network as the inference model, (2) warm-up period to support stochastic units staying active in early training, and (3) use of batch normalization. Using these improvements we show state-of-the-art log-likelihood results for generative modeling on several benchmark datasets.",
author = "S{\o}nderby, {Casper Kaae} and Tapani Raiko and Lars Maal{\o}e and S{\o}nderby, {S{\o}ren Kaae} and Ole Winther",
year = "2016",
language = "English",
booktitle = "Proceedings of the 33rd International Conference on Machine Learning (ICML 2016)",

}

Sønderby, CK, Raiko, T, Maaløe, L, Sønderby, SK & Winther, O 2016, How to Train Deep Variational Autoencoders and Probabilistic Ladder Networks. in Proceedings of the 33rd International Conference on Machine Learning (ICML 2016). JMLR: Workshop and Conference Proceedings, vol. 48, 33rd International Conference on Machine Learning (ICML 2016), New York, United States, 19/06/2016.

How to Train Deep Variational Autoencoders and Probabilistic Ladder Networks. / Sønderby, Casper Kaae; Raiko, Tapani; Maaløe, Lars; Sønderby, Søren Kaae; Winther, Ole.

Proceedings of the 33rd International Conference on Machine Learning (ICML 2016). 2016. (JMLR: Workshop and Conference Proceedings, Vol. 48).

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

TY - GEN

T1 - How to Train Deep Variational Autoencoders and Probabilistic Ladder Networks

AU - Sønderby, Casper Kaae

AU - Raiko, Tapani

AU - Maaløe, Lars

AU - Sønderby, Søren Kaae

AU - Winther, Ole

PY - 2016

Y1 - 2016

N2 - Variational autoencoders are a powerful framework for unsupervised learning. However, previous work has been restricted to shallow models with one or two layers of fully factorized stochastic latent variables, limiting the flexibility of the latent representation. We propose three advances in training algorithms of variational autoencoders, for the first time allowing to train deep models of up to five stochastic layers, (1) using a structure similar to the Ladder network as the inference model, (2) warm-up period to support stochastic units staying active in early training, and (3) use of batch normalization. Using these improvements we show state-of-the-art log-likelihood results for generative modeling on several benchmark datasets.

AB - Variational autoencoders are a powerful framework for unsupervised learning. However, previous work has been restricted to shallow models with one or two layers of fully factorized stochastic latent variables, limiting the flexibility of the latent representation. We propose three advances in training algorithms of variational autoencoders, for the first time allowing to train deep models of up to five stochastic layers, (1) using a structure similar to the Ladder network as the inference model, (2) warm-up period to support stochastic units staying active in early training, and (3) use of batch normalization. Using these improvements we show state-of-the-art log-likelihood results for generative modeling on several benchmark datasets.

M3 - Article in proceedings

BT - Proceedings of the 33rd International Conference on Machine Learning (ICML 2016)

ER -

Sønderby CK, Raiko T, Maaløe L, Sønderby SK, Winther O. How to Train Deep Variational Autoencoders and Probabilistic Ladder Networks. In Proceedings of the 33rd International Conference on Machine Learning (ICML 2016). 2016. (JMLR: Workshop and Conference Proceedings, Vol. 48).