Towards Optimal Running Times for Optimal Transport.

In this work, we provide faster algorithms for approximating the optimal transport distance, e.g. earth moveru0027s distance, between two discrete probability distributions $mu, nu Delta^n$. Given a cost function $C : [n] times [n] mathbb{R}_{geq 0}$ where $C(i,j)$ quantifies the penalty of transporting a unit of mass from $i$ to $j$, we show how to compute a coupling $X$ between $r$ and $c$ in time $widetilde{O}left(n^2 /epsilon right)$ whose expected transportation cost is within an additive $epsilon$ of optimal, where we have assumed that the largest entry of $C$ is bounded by a constant. This improves upon the previously best known running time for this problem of $widetilde{O}left(minleft{ n^{9/4}/epsilon, n^2/epsilon^2 right}right)$. We achieve our results by providing reductions from optimal transport to canonical optimization problems for which recent algorithmic efforts have provided nearly-linear time algorithms. Leveraging nearly linear time algorithms for solving packing linear programs and for solving the matrix balancing problem, we obtain two separate proofs of our stated running time. Moreover, we show that further algorithmic improvements to our result would be surprising in the sense that any improvement would yield an $o(n^{2.5})$ algorithm for textit{maximum cardinality bipartite matching}, for which currently the only known algorithms for achieving such a result are based on fast-matrix multiplication.