On the Identifiability of Nonlinear ICA: Sparsity and Beyond

arXiv:2206.07751v5 Announce Type: replace
Abstract: Nonlinear independent component analysis (ICA) aims to recover the underlying independent latent sources from their observable nonlinear mixtures. How to make the nonlinear ICA model identifiable up to certain trivial indeterminacies is a long-standing problem in unsupervised learning. Recent breakthroughs reformulate the standard independence assumption of sources as conditional independence given some auxiliary variables (e.g., class labels and/or domain/time indexes) as weak supervision or inductive bias. However, nonlinear ICA with unconditional priors cannot benefit from …

abstract analysis arxiv beyond cs.ai cs.lg independent observable sparsity standard stat.ml type unsupervised unsupervised learning