2020/05/02 by Shmuel Friedland, Friedland, Shmuel
Mathematics · #Markov Chains and Monte Carlo Methods #Mathematical Approximation and Integration #Tensor decomposition and applications
paper · pdf · doi:10.48550/arxiv.2005.00945
We study the optimal transport problem for d>2 discrete measures. This is a linear programming problem on d-tensors. It gives a way to compute a "distance" between two sets of discrete measures. We introduce an entropic regularization term, which gives rise to a scaling of tensors. We give a variation of the celebrated Sinkhorn scaling algorithm. We show that this algorithm can be viewed as a partial minimization algorithm of a strictly convex function. Under appropriate conditions the rate of convergence is geometric and we estimate the rate. Our results are generalizations of known results for the classical case of two discrete measures.