arXiv Machine Learning By Soheun Yi, Yizhou Lu, Chandler Squires, Pradeep Ravikumar

Concept Modulation Models: A Unified Framework for Identifiability and Extrapolation

Read the original on arXiv Machine Learning →

arXiv:2606. 18509v1 Announce Type: new Abstract: Reliable generalization in conditional latent variable models requires understanding both identifiability and extrapolation: how observed variation across attributes determines latent structure, and how that structure determines distributions at unseen attributes.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
Jul 28

Beyond ICA: Identifiability by Symmetry Breaking

arXiv:2607. 23182v1 Announce Type: cross 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.

By Pengzhou Wu