2021-03-18-camuto21b.md

title	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Learning Bijective Feature Maps for Linear ICA	Separating high-dimensional data like images into independent latent factors, i.e independent component analysis (ICA), remains an open research problem. As we show, existing probabilistic deep generative models (DGMs), which are tailor-made for image data, underperform on non-linear ICA tasks. To address this, we propose a DGM which combines bijective feature maps with a linear ICA model to learn interpretable latent structures for high-dimensional data. Given the complexities of jointly training such a hybrid model, we introduce novel theory that constrains linear ICA to lie close to the manifold of orthogonal rectangular matrices, the Stiefel manifold. By doing so we create models that converge quickly, are easy to train, and achieve better unsupervised latent factor discovery than flow-based models, linear ICA, and Variational Autoencoders on images.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	camuto21b	0	Learning Bijective Feature Maps for Linear ICA	3655	3663	3655-3663	3655	false	Camuto, Alexander and Willetts, Matthew and Holmes, Chris and Paige, Brooks and Roberts, Stephen	given family Alexander Camuto given family Matthew Willetts given family Chris Holmes given family Brooks Paige given family Stephen Roberts	2021-03-18		Proceedings of The 24th International Conference on Artificial Intelligence and Statistics	130	inproceedings	date-parts 2021 3 18	http://proceedings.mlr.press/v130/camuto21b/camuto21b.pdf	label link Supplementary ZIP http://proceedings.mlr.press/v130/camuto21b/camuto21b-supp.zip