Author

M. Besserve

h-index 17 View on Semantic Scholar

We have 1 of 55 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#data science 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