AI Chat AI Image Generator AI Video Text to Speech

The GenCol algorithm for high-dimensional optimal transport: general formulation and application to barycenters and Wasserstein splines

09/19/2022

∙

by Gero Friesecke, et al.

∙

∙

We extend the recently introduced genetic column generation algorithm for high-dimensional multi-marginal optimal transport from symmetric to general problems. We use the algorithm to calculate accurate mesh-free Wasserstein barycenters and cubic Wasserstein splines.

Gero Friesecke
4 publications
Maximilian Penka
2 publications

research

∙ 03/13/2023

Convergence proof for the GenCol algorithm in the case of two-marginal optimal transport

The recently introduced Genetic Column Generation (GenCol) algorithm has...

0 Gero Friesecke, et al. ∙

research

∙ 02/05/2021

Learning High Dimensional Wasserstein Geodesics

We propose a new formulation and learning strategy for computing the Was...

19 Shu Liu, et al. ∙

research

∙ 02/18/2021

A Mathematical Principle of Deep Learning: Learn the Geodesic Curve in the Wasserstein Space

Recent studies revealed the mathematical connection of deep neural netwo...

0 Kuo Gai, et al. ∙

research

∙ 03/23/2021

Genetic column generation: Fast computation of high-dimensional multi-marginal optimal transport problems

We introduce a simple, accurate, and extremely efficient method for nume...

0 Gero Friesecke, et al. ∙

research

∙ 05/28/2018

Bayesian Learning with Wasserstein Barycenters

In this work we introduce a novel paradigm for Bayesian learning based o...

0 Gonzalo Rios, et al. ∙

research

∙ 11/16/2021

Ocean Mover's Distance: Using Optimal Transport for Analyzing Oceanographic Data

Modern ocean datasets are large, multi-dimensional, and inherently spati...

0 Sangwon Hyun, et al. ∙

research

∙ 11/08/2022

Scalable multi-class sampling via filtered sliced optimal transport

We propose a multi-class point optimization formulation based on continu...

0 Corentin Salaün, et al. ∙