On Unbalanced Optimal Transport: An Analysis of Sinkhorn Algorithm

arXiv2002.03293MaRDI QIDQ6334402FDOQ6334402

Authors: Khiem Pham, Khang Le, Nhat Ho, Tung Pham, Hung Bui 

Publication date: 9 February 2020

Abstract: We provide a computational complexity analysis for the Sinkhorn algorithm that solves the entropic regularized Unbalanced Optimal Transport (UOT) problem between two measures of possibly different masses with at most $n$ components. We show that the complexity of the Sinkhorn algorithm for finding an $varepsilon$-approximate solution to the UOT problem is of order $widetildemathcalO(n^2/varepsilon)$, which is near-linear time. To the best of our knowledge, this complexity is better than the complexity of the Sinkhorn algorithm for solving the Optimal Transport (OT) problem, which is of order $widetildemathcalO(n^2/varepsilo{n}^2)$. Our proof technique is based on the geometric convergence of the Sinkhorn updates to the optimal dual solution of the entropic regularized UOT problem and some properties of the primal solution. It is also different from the proof for the complexity of the Sinkhorn algorithm for approximating the OT problem since the UOT solution does not have to meet the marginal constraints.

Has companion code repository: https://github.com/lntk/uot

This page was built for publication: On Unbalanced Optimal Transport: An Analysis of Sinkhorn Algorithm

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6334402)