Identifiability of Potentially Degenerate Gaussian Mixture Models With Piecewise Affine Mixing

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Xu, Danru, Lachapelle, Sébastien, Magliacane, Sara
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908964898209792
author Xu, Danru
Lachapelle, Sébastien
Magliacane, Sara
author_facet Xu, Danru
Lachapelle, Sébastien
Magliacane, Sara
contents Causal representation learning (CRL) aims to identify the underlying latent variables from high-dimensional observations, even when variables are dependent with each other. We study this problem for latent variables that follow a potentially degenerate Gaussian mixture distribution and that are only observed through the transformation via a piecewise affine mixing function. We provide a series of progressively stronger identifiability results for this challenging setting in which the probability density functions are ill-defined because of the potential degeneracy. For identifiability up to permutation and scaling, we leverage a sparsity regularization on the learned representation. Based on our theoretical results, we propose a two-stage method to estimate the latent variables by enforcing sparsity and Gaussianity in the learned representations. Experiments on synthetic and image data highlight our method's effectiveness in recovering the ground-truth latent variables.
format Preprint
id arxiv_https___arxiv_org_abs_2604_13218
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Identifiability of Potentially Degenerate Gaussian Mixture Models With Piecewise Affine Mixing
Xu, Danru
Lachapelle, Sébastien
Magliacane, Sara
Machine Learning
Artificial Intelligence
Statistics Theory
Causal representation learning (CRL) aims to identify the underlying latent variables from high-dimensional observations, even when variables are dependent with each other. We study this problem for latent variables that follow a potentially degenerate Gaussian mixture distribution and that are only observed through the transformation via a piecewise affine mixing function. We provide a series of progressively stronger identifiability results for this challenging setting in which the probability density functions are ill-defined because of the potential degeneracy. For identifiability up to permutation and scaling, we leverage a sparsity regularization on the learned representation. Based on our theoretical results, we propose a two-stage method to estimate the latent variables by enforcing sparsity and Gaussianity in the learned representations. Experiments on synthetic and image data highlight our method's effectiveness in recovering the ground-truth latent variables.
title Identifiability of Potentially Degenerate Gaussian Mixture Models With Piecewise Affine Mixing
topic Machine Learning
Artificial Intelligence
Statistics Theory
url https://arxiv.org/abs/2604.13218