Dual Regularized Optimal Transport

12/05/2020
by   Rishi Sonthalia, et al.
1

In this paper, we present a new formulation of unbalanced optimal transport called Dual Regularized Optimal Transport (DROT). We argue that regularizing the dual formulation of optimal transport results in a version of unbalanced optimal transport that leads to sparse solutions and that gives us control over mass creation and destruction. We build intuition behind such control and present theoretical properties of the solutions to DROT. We demonstrate that due to recent advances in optimization techniques, we can feasibly solve such a formulation at large scales and present extensive experimental evidence for this formulation and its solution.

READ FULL TEXT

page 6

page 7

research
09/20/2023

Error estimate for regularized optimal transport problems via Bregman divergence

Regularization by the Shannon entropy enables us to efficiently and appr...
research
10/12/2022

Gaussian Processes on Distributions based on Regularized Optimal Transport

We present a novel kernel over the space of probability measures based o...
research
08/05/2022

Efficient and Exact Multimarginal Optimal Transport with Pairwise Costs

In this paper, we address the numerical solution to the multimarginal op...
research
05/24/2023

Generative Modeling through the Semi-dual Formulation of Unbalanced Optimal Transport

Optimal Transport (OT) problem investigates a transport map that bridges...
research
01/06/2021

Fairness with Continuous Optimal Transport

Whilst optimal transport (OT) is increasingly being recognized as a powe...
research
04/27/2022

The Multimarginal Optimal Transport Formulation of Adversarial Multiclass Classification

We study a family of adversarial multiclass classification problems and ...
research
09/30/2022

Neural Unbalanced Optimal Transport via Cycle-Consistent Semi-Couplings

Comparing unpaired samples of a distribution or population taken at diff...

Please sign up or login with your details

Forgot password? Click here to reset