Domain decomposition for entropy regularized optimal transport

01/29/2020
by   Mauro Bonafini, et al.
0

We study Benamou's domain decomposition algorithm for optimal transport in the entropy regularized setting. The key observation is that the regularized variant converges to the globally optimal solution under very mild assumptions. We prove linear convergence of the algorithm with respect to the Kullback–Leibler divergence and illustrate the (potentially very slow) rates with numerical examples. On problems with sufficient geometric structure (such as Wasserstein distances between images) we expect much faster convergence. We then discuss important aspects of a computationally efficient implementation, such as adaptive sparsity, a coarse-to-fine scheme and parallelization, paving the way to numerically solving large-scale optimal transport problems. We demonstrate efficient numerical performance for computing the Wasserstein-2 distance between 2D images and observe that, even without parallelization, domain decomposition compares favorably to applying a single efficient implementation of the Sinkhorn algorithm in terms of runtime, memory and solution quality.

READ FULL TEXT

page 2

page 34

page 36

page 37

research
12/19/2020

Entropy-regularized optimal transport on multivariate normal and q-normal distributions

Distance and divergence of the probability measures play a central role ...
research
06/15/2021

Asymptotic analysis of domain decomposition for optimal transport

Large optimal transport problems can be approached via domain decomposit...
research
08/26/2023

Optimal Transport-inspired Deep Learning Framework for Slow-Decaying Problems: Exploiting Sinkhorn Loss and Wasserstein Kernel

Reduced order models (ROMs) are widely used in scientific computing to t...
research
02/16/2021

Efficient Discretizations of Optimal Transport

Obtaining solutions to Optimal Transportation (OT) problems is typically...
research
05/29/2023

Bringing regularized optimal transport to lightspeed: a splitting method adapted for GPUs

We present an efficient algorithm for regularized optimal transport. In ...
research
12/07/2017

Gini-regularized Optimal Transport with an Application to Spatio-Temporal Forecasting

Rapidly growing product lines and services require a finer-granularity f...
research
02/25/2021

Improving Approximate Optimal Transport Distances using Quantization

Optimal transport (OT) is a popular tool in machine learning to compare ...

Please sign up or login with your details

Forgot password? Click here to reset