Online Sinkhorn: optimal transportation distances from sample streams

03/03/2020
by   Arthur Mensch, et al.
17

Optimal Transport (OT) distances are now routinely used as loss functions in ML tasks. Yet, computing OT distances between arbitrary (i.e. not necessarily discrete) probability distributions remains an open problem. This paper introduces a new online estimator of entropy-regularized OT distances between two such arbitrary distributions. It uses streams of samples from both distributions to iteratively enrich a non-parametric representation of the transportation plan. Compared to the classic Sinkhorn algorithm, our method leverages new samples at each iteration, which enables a consistent estimation of the true regularized OT distance. We cast our algorithm as a block-convex mirror descent in the space of positive distributions, and provide a theoretical analysis of its convergence. We numerically illustrate the performance of our method in comparison with concurrent approaches.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/22/2016

Continuous-Flow Graph Transportation Distances

Optimal transportation distances are valuable for comparing and analyzin...
research
04/26/2017

Quadratically-Regularized Optimal Transport on Graphs

Optimal transportation provides a means of lifting distances between poi...
research
10/01/2019

Training Generative Networks with general Optimal Transport distances

We propose a new algorithm that uses an auxiliary Neural Network to calc...
research
10/18/2018

Interpolating between Optimal Transport and MMD using Sinkhorn Divergences

Comparing probability distributions is a fundamental problem in data sci...
research
10/28/2019

Adaptive Sampling for Estimating Multiple Probability Distributions

We consider the problem of allocating samples to a finite set of discret...
research
12/14/2020

Outlier-Robust Optimal Transport

Optimal transport (OT) provides a way of measuring distances between dis...
research
06/04/2013

Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances

Optimal transportation distances are a fundamental family of parameteriz...

Please sign up or login with your details

Forgot password? Click here to reset