Smooth and Sparse Optimal Transport

10/17/2017
by   Mathieu Blondel, et al.
0

Entropic regularization is quickly emerging as a new standard in optimal transport (OT). It enables to cast the OT computation as a differentiable and unconstrained convex optimization problem, which can be efficiently solved using the Sinkhorn algorithm. However, the entropy term keeps the transportation plan strictly positive and therefore completely dense, unlike unregularized OT. This lack of sparsity can be problematic for applications where the transportation plan itself is of interest. In this paper, we explore regularizing both the primal and dual original formulations with an arbitrary strongly convex term. We show that this corresponds to relaxing dual and primal constraints with approximate smooth constraints. We show how to incorporate squared 2-norm and group lasso regularizations within that framework, leading to sparse and group-sparse transportation plans. On the theoretical side, we are able to bound the approximation error introduced by smoothing the original primal and dual formulations. Our results suggest that, for the smoothed dual, the approximation error can often be smaller with squared 2-norm regularization than with entropic regularization. We showcase our proposed framework on the task of color transfer.

READ FULL TEXT
research
09/30/2022

Sparsity-Constrained Optimal Transport

Regularized optimal transport (OT) is now increasingly used as a loss or...
research
07/21/2013

Regularized Discrete Optimal Transport

This article introduces a generalization of the discrete optimal transpo...
research
03/06/2015

Convex Color Image Segmentation with Optimal Transport Distances

This work is about the use of regularized optimal-transport distances fo...
research
07/22/2023

Sparse Index Tracking: Simultaneous Asset Selection and Capital Allocation via ℓ_0-Constrained Portfolio

Sparse index tracking is one of the prominent passive portfolio manageme...
research
06/09/2020

The statistical effect of entropic regularization in optimal transportation

We propose to tackle the problem of understanding the effect of regulari...
research
01/16/2012

A General Framework of Dual Certificate Analysis for Structured Sparse Recovery Problems

This paper develops a general theoretical framework to analyze structure...
research
01/06/2021

Bayesian Inference of Random Dot Product Graphs via Conic Programming

We present a convex cone program to infer the latent probability matrix ...

Please sign up or login with your details

Forgot password? Click here to reset