AI RESEARCH
Disentanglement Beyond Generative Models with Riemannian ICA
arXiv CS.LG
•
ArXi:2605.22531v1 Announce Type: new There is a gap between the theoretical foundations of disentanglement and the practice of modern representation learning. Existing theoretical frameworks, particularly Independent Component Analysis (ICA) and its nonlinear variants, assume a generative model with statistically independent latent variables underlying the data so that disentanglement amounts to identifying the latents that could have generated the data.