This is the public, feature-limited version of the conference webpage. After Registration and login please visit the full version.

ICE-BeeM: Identifiable Conditional Energy-Based Deep Models Based on Nonlinear ICA

Ilyes Khemakhem, Ricardo Monti, Diederik P. Kingma, Aapo Hyvarinen

Spotlight presentation: Orals & Spotlights Track 15: COVID/Applications/Composition
on 2020-12-09T07:20:00-08:00 - 2020-12-09T07:30:00-08:00
Poster Session 4 (more posters)
on 2020-12-09T09:00:00-08:00 - 2020-12-09T11:00:00-08:00
Abstract: We consider the identifiability theory of probabilistic models and establish sufficient conditions under which the representations learnt by a very broad family of conditional energy-based models are unique in function space, up to a simple transformation. In our model family, the energy function is the dot-product between two feature extractors, one for the dependent variable, and one for the conditioning variable. We show that under mild conditions, the features are unique up to scaling and permutation. Our results extend recent developments in nonlinear ICA, and in fact, they lead to an important generalization of ICA models. In particular, we show that our model can be used for the estimation of the components in the framework of Independently Modulated Component Analysis (IMCA), a new generalization of nonlinear ICA that relaxes the independence assumption. A thorough empirical study show that representations learnt by our model from real-world image datasets are identifiable, and improve performance in transfer learning and semi-supervised learning tasks.

Preview Video and Chat

To see video, interact with the author and ask questions please use registration and login.