Sliced Multi-Marginal Optimal Transport

02/14/2021
by   Samuel Cohen, et al.
0

We study multi-marginal optimal transport, a generalization of optimal transport that allows us to define discrepancies between multiple measures. It provides a framework to solve multi-task learning problems and to perform barycentric averaging. However, multi-marginal distances between multiple measures are typically challenging to compute because they require estimating a transport plan with N^P variables. In this paper, we address this issue in the following way: 1) we efficiently solve the one-dimensional multi-marginal Monge-Wasserstein problem for a classical cost function in closed form, and 2) we propose a higher-dimensional multi-marginal discrepancy via slicing and study its generalized metric properties. We show that computing the sliced multi-marginal discrepancy is massively scalable for a large number of probability measures with support as large as 10^7 samples. Our approach can be applied to solving problems such as barycentric averaging, multi-task density estimation and multi-task reinforcement learning.

READ FULL TEXT
research
12/23/2022

An ODE characterisation of multi-marginal optimal transport

The purpose of this paper is to introduce a new numerical method to solv...
research
01/29/2020

Multi-Marginal Optimal Transport Defines a Generalized Metric

We prove that the multi-marginal optimal transport (MMOT) problem define...
research
05/20/2018

Wasserstein regularization for sparse multi-task regression

Two important elements have driven recent innovation in the field of reg...
research
08/22/2023

Data Assimilation for Sign-indefinite Priors: A generalization of Sinkhorn's algorithm

The purpose of this work is to develop a framework to calibrate signed d...
research
02/05/2021

Constrained overdamped Langevin dynamics for symmetric multimarginal optimal transportation

The Strictly Correlated Electrons (SCE) limit of the Levy-Lieb functiona...
research
05/13/2022

Multi-Marginal Gromov-Wasserstein Transport and Barycenters

Gromov-Wasserstein (GW) distances are generalizations of Gromov-Haussdor...
research
02/02/2022

Approximative Algorithms for Multi-Marginal Optimal Transport and Free-Support Wasserstein Barycenters

Computationally solving multi-marginal optimal transport (MOT) with squa...

Please sign up or login with your details

Forgot password? Click here to reset