Discovery of Single Independent Latent Variable

Uri Shaham, Jonathan Svirsky, Ori Katz, Ronen Talmon

NeurIPS 2022

/neurips/2022/shaham2022neurips-discovery/

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.

PDF NeurIPS OpenReview Semantic Scholar

Cite

Text

Shaham et al. "Discovery of Single Independent Latent Variable." Neural Information Processing Systems, 2022.

Markdown

[Shaham et al. "Discovery of Single Independent Latent Variable." Neural Information Processing Systems, 2022.](https://mlanthology.org/neurips/2022/shaham2022neurips-discovery/)

BibTeX

@inproceedings{shaham2022neurips-discovery,
  title     = {{Discovery of Single Independent Latent Variable}},
  author    = {Shaham, Uri and Svirsky, Jonathan and Katz, Ori and Talmon, Ronen},
  booktitle = {Neural Information Processing Systems},
  year      = {2022},
  url       = {https://mlanthology.org/neurips/2022/shaham2022neurips-discovery/}
}