ICE-BeeM: Identifiable Conditional Energy-Based Deep Models Based on Nonlinear ICA
NIPS 2020, 2020.
We further prove a fundamental connection between energy-based models and latent variable models, showing that ICE-BeeM is able to estimate nonlinear ICA, as a special case
We consider the identifiability theory of probabilistic models and establish sufficient conditions under which the representations learned 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 ex...More
PPT (Upload PPT)