OT-ICA

OT-ICA: Linear Independent Component Analysis via Wasserstein Distance Optimization

A new arXiv preprint proposes OT-ICA, an algorithm for linear Independent Component Analysis that replaces classical proxy contrast functions (cumulants, parametric likelihoods) with the squared Wasserstein-2 distance to a standard Gaussian as a non-Gaussianity measure. The authors prove that maximizing this distance over linear projections recovers independent components, then implement gradient-based optimization. Empirical results on simulated data show OT-ICA outperforms proxy-based methods, with applied validation on EEG artifact removal and econometric price discovery.