Subspace Robust Wasserstein Distances
[edit]
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:50725081, 2019.
Abstract
Making sense of Wasserstein distances between discrete measures in highdimensional settings remains a challenge. Recent work has advocated a twostep approach to improve robustness and facilitate the computation of optimal transport, using for instance projections on random real lines, or a preliminary quantization of the measures to reduce the size of their support. We propose in this work a “maxmin” robust variant of the Wasserstein distance by considering the maximal possible distance that can be realized between two measures, assuming they can be projected orthogonally on a lower kdimensional subspace. Alternatively, we show that the corresponding “minmax” OT problem has a tight convex relaxation which can be cast as that of finding an optimal transport plan with a low transportation cost, where the cost is alternatively defined as the sum of the k largest eigenvalues of the second order moment matrix of the displacements (or matchings) corresponding to that plan (the usual OT definition only considers the trace of that matrix). We show that both quantities inherit several favorable properties from the OT geometry. We propose two algorithms to compute the latter formulation using entropic regularization, and illustrate the interest of this approach empirically.
Related Material


