Competitive training of mixtures of independent deep generative models

Locatello F, Vincent D, Tolstikhin I, Rätsch G, Gelly S, Schölkopf B. Competitive training of mixtures of independent deep generative models. arXiv, 1804.11130.

Download (ext.)

Preprint | Submitted | English
Author
Locatello, FrancescoISTA ; Vincent, Damien; Tolstikhin, Ilya; Rätsch, Gunnar; Gelly, Sylvain; Schölkopf, Bernhard
Department
Abstract
A common assumption in causal modeling posits that the data is generated by a set of independent mechanisms, and algorithms should aim to recover this structure. Standard unsupervised learning, however, is often concerned with training a single model to capture the overall distribution or aspects thereof. Inspired by clustering approaches, we consider mixtures of implicit generative models that ``disentangle'' the independent generative mechanisms underlying the data. Relying on an additional set of discriminators, we propose a competitive training procedure in which the models only need to capture the portion of the data distribution from which they can produce realistic samples. As a by-product, each model is simpler and faster to train. We empirically show that our approach splits the training distribution in a sensible way and increases the quality of the generated samples.
Publishing Year
Date Published
2018-04-30
Journal Title
arXiv
Article Number
1804.11130
IST-REx-ID

Cite this

Locatello F, Vincent D, Tolstikhin I, Rätsch G, Gelly S, Schölkopf B. Competitive training of mixtures of independent deep generative models. arXiv. doi:10.48550/arXiv.1804.11130
Locatello, F., Vincent, D., Tolstikhin, I., Rätsch, G., Gelly, S., & Schölkopf, B. (n.d.). Competitive training of mixtures of independent deep generative models. arXiv. https://doi.org/10.48550/arXiv.1804.11130
Locatello, Francesco, Damien Vincent, Ilya Tolstikhin, Gunnar Rätsch, Sylvain Gelly, and Bernhard Schölkopf. “Competitive Training of Mixtures of Independent Deep Generative Models.” ArXiv, n.d. https://doi.org/10.48550/arXiv.1804.11130.
F. Locatello, D. Vincent, I. Tolstikhin, G. Rätsch, S. Gelly, and B. Schölkopf, “Competitive training of mixtures of independent deep generative models,” arXiv. .
Locatello F, Vincent D, Tolstikhin I, Rätsch G, Gelly S, Schölkopf B. Competitive training of mixtures of independent deep generative models. arXiv, 1804.11130.
Locatello, Francesco, et al. “Competitive Training of Mixtures of Independent Deep Generative Models.” ArXiv, 1804.11130, doi:10.48550/arXiv.1804.11130.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]

Link(s) to Main File(s)
Access Level
OA Open Access

Export

Marked Publications

Open Data ISTA Research Explorer

Sources

arXiv 1804.11130

Search this title in

Google Scholar