# Non-linear ICA based on Cramer-Wold metric

arXiv: https://arxiv.org/abs/1903.00201 · HTML: https://mlsanity.com/paper/1903.00201/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Mar 2019.

## Built on by (most cited first, 3 of 3)

- [PluGeN: Multi-Label Conditional Generation From Pre-Trained Models](https://mlsanity.com/paper/2109.09011/) (2021)
- [On the relationship between disentanglement and multi-task learning](https://mlsanity.com/paper/2110.03498/) (2021)
- [Disentangling Autoencoders (DAE)](https://mlsanity.com/paper/2202.09926/) (2022)

## Abstract (arXiv)

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.