Beyond independent component analysis: identifiability and algorithms

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ribot, Alvaro, Seigal, Anna, Zwiernik, Piotr
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918157077184512
author Ribot, Alvaro
Seigal, Anna
Zwiernik, Piotr
author_facet Ribot, Alvaro
Seigal, Anna
Zwiernik, Piotr
contents Independent Component Analysis (ICA) is a classical method for recovering latent variables with useful identifiability properties. For independent variables, cumulant tensors are diagonal; relaxing independence yields tensors whose zero structure generalizes diagonality. These models have been the subject of recent work in non-independent component analysis. We show that pairwise mean independence answers the question of how much one can relax independence: it is identifiable, any weaker notion is non-identifiable, and it contains the models previously studied as special cases. Our results apply to distributions with the required zero pattern at any cumulant tensor. We propose an algebraic recovery algorithm based on least-squares optimization over the orthogonal group. Simulations highlight robustness: enforcing full independence can harm estimation, while pairwise mean independence enables more stable recovery. These findings extend the classical ICA framework and provide a rigorous basis for blind source separation beyond independence.
format Preprint
id arxiv_https___arxiv_org_abs_2510_07525
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Beyond independent component analysis: identifiability and algorithms
Ribot, Alvaro
Seigal, Anna
Zwiernik, Piotr
Statistics Theory
Machine Learning
62H12, 62R01, 62E10, 15A69
Independent Component Analysis (ICA) is a classical method for recovering latent variables with useful identifiability properties. For independent variables, cumulant tensors are diagonal; relaxing independence yields tensors whose zero structure generalizes diagonality. These models have been the subject of recent work in non-independent component analysis. We show that pairwise mean independence answers the question of how much one can relax independence: it is identifiable, any weaker notion is non-identifiable, and it contains the models previously studied as special cases. Our results apply to distributions with the required zero pattern at any cumulant tensor. We propose an algebraic recovery algorithm based on least-squares optimization over the orthogonal group. Simulations highlight robustness: enforcing full independence can harm estimation, while pairwise mean independence enables more stable recovery. These findings extend the classical ICA framework and provide a rigorous basis for blind source separation beyond independence.
title Beyond independent component analysis: identifiability and algorithms
topic Statistics Theory
Machine Learning
62H12, 62R01, 62E10, 15A69
url https://arxiv.org/abs/2510.07525