PaperScope
LIVE · 2026-09-29 05:40 UTC

Towards Identifiable Representations under Misspecified Structure

Yuke Li, Yujia Zheng, Ziyi Chen, Kun Zhang, Heng Huang

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.33273 v1
Category
Submitted
2026-09-27

Abstract

The presence of noise that depends on the latent variables poses a fundamental challenge to identifiability. Existing results rely on conditional independence among the observations given the latent variables. We study a more general \emph{misspecified structure}, where this conditional factorization does not hold, and establish both precise and approximate identifiability guarantees. We characterize structural misspecification as a perturbed factor analysis problem. For precise identifiability, we establish subspace identifiability under spectral separation and controlled perturbation, followed by component-wise identifiability under structural sparsity. When the precise condition is not guaranteed, we derive an approximate subspace-identifiability theorem. Based on these results, we develop an unsupervised variational estimator for recovering latent variables. Experiments demonstrate the effectiveness of the proposed framework.

arXiv abs page · PDF · same-day batch