FastICA with Learned Scores from the Empirical Characteristic Function

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Watts, David, Manton, Jonathan H.
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913058312421376
author Watts, David
Manton, Jonathan H.
author_facet Watts, David
Manton, Jonathan H.
contents Independent component analysis (ICA) estimates a demixing matrix that can recover statistically independent sources from linear mixtures. FastICA is a popular ICA algorithm due to its efficiency, but its performance strongly depends on a user-chosen nonlinear function matched to the source distribution. When the source distribution is unknown, this function must be guessed at, and incorrect guesses can lead to significant drops in performance. We remove the need to guess by estimating a suitable function directly from the observed data. Our experiments show that the separation error stays close to the best fixed choice across synthetic mixtures comprising heavy-tailed or discrete sources while retaining a FastICA-like runtime.
format Preprint
id arxiv_https___arxiv_org_abs_2604_22125
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle FastICA with Learned Scores from the Empirical Characteristic Function
Watts, David
Manton, Jonathan H.
Signal Processing
Independent component analysis (ICA) estimates a demixing matrix that can recover statistically independent sources from linear mixtures. FastICA is a popular ICA algorithm due to its efficiency, but its performance strongly depends on a user-chosen nonlinear function matched to the source distribution. When the source distribution is unknown, this function must be guessed at, and incorrect guesses can lead to significant drops in performance. We remove the need to guess by estimating a suitable function directly from the observed data. Our experiments show that the separation error stays close to the best fixed choice across synthetic mixtures comprising heavy-tailed or discrete sources while retaining a FastICA-like runtime.
title FastICA with Learned Scores from the Empirical Characteristic Function
topic Signal Processing
url https://arxiv.org/abs/2604.22125