Preprint
Jul 2026
Linear Independent Component Analysis via Optimal Transport
It is proved that the Wasserstein distance between a standard normal distribution and linear projections of the data is maximized when the projection recovers an independent component, and the OT-ICA algorithm which finds this projection by gradient-based optimization is proposed.
Ashutosh Jha, M. Besserve, Simon Buchholz
· 1 citation