AI RESEARCH
Provable Affine Identifiability of Nonlinear CCA under Latent Distributional Priors
arXiv CS.LG
•
ArXi:2510.04758v2 Announce Type: replace In this work, we establish the sufficient conditions under which nonlinear Canonical Correlation Analysis (CCA) recovers ground-truth latent factors up to an affine transformation. By transporting the analysis from the observation space to the source space, we extend classical statistical results on orthogonal polynomial expansions of bivariate distributions to representation learning, proving affine identifiability under specific distributional priors.