SyncAI.news, a Varaisys broadcasting
Towards Identifiable Representations under Misspecified Structure
YL

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

· 1 min read

ResearcharXiv cs.LG

Towards Identifiable Representations under Misspecified Structure

arXiv:2609.33273v1 Announce Type: new 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.

Original source

This story was published by arXiv cs.LG and written by Yuke Li, Yujia Zheng, Ziyi Chen, Kun Zhang, Heng Huang. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News