Discovery of Single Independent Latent Variable
Abstract
Latent variable discovery is a central problem in data analysis with a broad range of applications in applied science. In this work, we consider data given as an invertible mixture of two statistically independent components and assume that one of the components is observed while the other is hidden. Our goal is to recover the hidden component. For this purpose, we propose an autoencoder equipped with a discriminator. Unlike the standard nonlinear ICA problem, which was shown to be non-identifiable, in the special case of ICA we consider here, we show that our approach can recover the component of interest up to entropy-preserving transformation. We demonstrate the performance of the proposed approach in several tasks, including image synthesis, voice cloning, and fetal ECG extraction.
Keywords
Cite
@article{arxiv.2110.05887,
title = {Discovery of Single Independent Latent Variable},
author = {Uri Shaham and Jonathan Svirsky and Ori Katz and Ronen Talmon},
journal= {arXiv preprint arXiv:2110.05887},
year = {2023}
}
Comments
Published as a conference paper at Neurips 2022. In the current version the proof of the lemma is modified