On the Connection between Dynamical Optimal Transport and Functional Lifting

07/06/2020
by   Thomas Vogt, et al.
0

Functional lifting methods provide a tool for approximating solutions of difficult non-convex problems by embedding them into a larger space. In this work, we investigate a mathematically rigorous formulation based on embedding into the space of pointwise probability measures over a fixed range Γ. Interestingly, this approach can be derived as a generalization of the theory of dynamical optimal transport. Imposing the established continuity equation as a constraint corresponds to variational models with first-order regularization. By modifying the continuity equation, the approach can also be extended to models with higher-order regularization.

READ FULL TEXT

page 32

page 33

page 34

research
09/16/2023

On the geometry and dynamical formulation of the Sinkhorn algorithm for optimal transport

The Sinkhorn algorithm is a numerical method for the solution of optimal...
research
10/04/2022

Neural Conservation Laws: A Divergence-Free Perspective

We investigate the parameterization of deep neural networks that by desi...
research
12/04/2019

Asymptotics for Strassen's Optimal Transport Problem

In this paper, we consider Strassen's version of optimal transport probl...
research
12/21/2020

A generalized conditional gradient method for dynamic inverse problems with optimal transport regularization

We develop a dynamic generalized conditional gradient method (DGCG) for ...
research
03/14/2023

An optimal transport regularized model to image reconstruction problems

Optimal transport problem has gained much attention in image processing ...
research
01/25/2022

Supervised learning of sheared distributions using linearized optimal transport

In this paper we study supervised learning tasks on the space of probabi...
research
07/02/2021

Data-driven mapping between functional connectomes using optimal transport

Functional connectomes derived from functional magnetic resonance imagin...

Please sign up or login with your details

Forgot password? Click here to reset