Entropic Regularisation of Robust Optimal Transport

05/29/2019
by   Rozenn Dahyot, et al.
0

Grogan et al [11,12] have recently proposed a solution to colour transfer by minimising the Euclidean distance L2 between two probability density functions capturing the colour distributions of two images (palette and target). It was shown to be very competitive to alternative solutions based on Optimal Transport for colour transfer. We show that in fact Grogan et al's formulation can also be understood as a new robust Optimal Transport based framework with entropy regularisation over marginals.

READ FULL TEXT
research
06/28/2023

Recent Advances in Optimal Transport for Machine Learning

Recently, Optimal Transport has been proposed as a probabilistic framewo...
research
12/19/2022

Fully Probabilistic Design for Optimal Transport

The goal of this paper is to introduce a new theoretical framework for O...
research
12/07/2021

Hypergraph Co-Optimal Transport: Metric and Categorical Properties

Hypergraphs capture multi-way relationships in data, and they have conse...
research
06/08/2019

A gradual, semi-discrete approach to generative network training via explicit wasserstein minimization

This paper provides a simple procedure to fit generative networks to tar...
research
04/19/2023

Generative Modeling of Time-Dependent Densities via Optimal Transport and Projection Pursuit

Motivated by the computational difficulties incurred by popular deep lea...
research
12/04/2021

Nonparametric mixture MLEs under Gaussian-smoothed optimal transport distance

The Gaussian-smoothed optimal transport (GOT) framework, pioneered in Go...
research
05/27/2022

Momentum Stiefel Optimizer, with Applications to Suitably-Orthogonal Attention, and Optimal Transport

The problem of optimization on Stiefel manifold, i.e., minimizing functi...

Please sign up or login with your details

Forgot password? Click here to reset