English

Data Driven Conditional Optimal Transport

Optimization and Control 2019-10-28 v1

Abstract

A data driven procedure is developed to compute the optimal map between two conditional probabilities ρ(xz1,...,zL)\rho(x|z_{1},...,z_{L}) and μ(yz1,...,zL)\mu(y|z_{1},...,z_{L}) depending on a set of covariates ziz_{i}. The procedure is tested on synthetic data from the ACIC Data Analysis Challenge 2017 and it is applied to non uniform lightness transfer between images. Exactly solvable examples and simulations are performed to highlight the differences with ordinary optimal transport.

Keywords

Cite

@article{arxiv.1910.11422,
  title  = {Data Driven Conditional Optimal Transport},
  author = {Esteban G. Tabak and Giulio Trigila and Wenjun Zhao},
  journal= {arXiv preprint arXiv:1910.11422},
  year   = {2019}
}
R2 v1 2026-06-23T11:54:19.169Z