arXiv stat.ML
· Papers
Beyond ICA: Identifiability by Symmetry Breaking
arXiv:2607.23182v1 Announce Type: new Abstract: We prove the identifiability of deep generative models (DGMs) with piecewise-affine (PWA) decoders and Gaussian mixture model (GMM) priors, in a purely unsupervised setting. We introduce three algebraic contrast principles for symmetry breaking: domain contrast, which tri