Non-linear ICA Based on Cramer-Wold Metric

Przemyslaw Spurek, Aleksandra Nowak, Jacek Tabor, Lukasz Maziarka, Stanislaw Jastrzebski

Abstract

Non-linear source separation is a challenging open problem with many applications. We extend a recently proposed Adversarial Non-linear ICA (ANICA) model and introduce Cramer-Wold ICA (CW-ICA). In contrast to ANICA, we use a simple, closed–form optimization target instead of a discriminator–based independence measure. Our results show that CW-ICA achieves comparable results to ANICA while foregoing the need for adversarial training.
BibTeX
@inproceedings{spurek2020non,
  author = {Przemyslaw Spurek and Aleksandra Nowak and Jacek Tabor and Lukasz Maziarka and Stanislaw Jastrzebski},
  title = {{Non-linear ICA Based on Cramer-Wold Metric}},
  booktitle = {ICONIP},
  year = {2020},
  url = {https://openreview.net/forum?id=dcKa8n4RJl},
}
Figure