Discovery of Single Independent Latent VariableDownload PDF

Published: 31 Oct 2022, Last Modified: 17 Dec 2022NeurIPS 2022 AcceptReaders: Everyone
Keywords: Independent Component revcovery
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.
Supplementary Material: pdf
15 Replies