Skip to yearly menu bar Skip to main content


Workshop

Clustering Meets Implicit Generative Models

Francesco Locatello · Damien Vincent · Ilya Tolstikhin · Gunnar Rätsch · Sylvain Gelly · Bernhard Schoelkopf

East Meeting Level 8 + 15 #10

Tue 1 May, 4:30 p.m. PDT

Clustering is a cornerstone of unsupervised learning which can be thought as disentangling multiple generative mechanisms underlying the data. In this paper we introduce an algorithmic framework to train mixtures of implicit generative models which we particularize for variational autoencoders. Relying on an additional set of discriminators, we propose a competitive procedure in which the models only need to approximate the portion of the data distribution from which they can produce realistic samples. As a byproduct, each model is simpler to train, and a clustering interpretation arises naturally from the partitioning of the training points among the models. We empirically show that our approach splits the training distribution in a reasonable way and increases the quality of the generated samples.

Live content is unavailable. Log in and register to view live content