Differentiable Cost-Parameterized Monge Map Estimators

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Howard, Samuel, Deligiannidis, George, Rebeschini, Patrick, Thornton, James
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914833059807232
author Howard, Samuel
Deligiannidis, George
Rebeschini, Patrick
Thornton, James
author_facet Howard, Samuel
Deligiannidis, George
Rebeschini, Patrick
Thornton, James
contents Within the field of optimal transport (OT), the choice of ground cost is crucial to ensuring that the optimality of a transport map corresponds to usefulness in real-world applications. It is therefore desirable to use known information to tailor cost functions and hence learn OT maps which are adapted to the problem at hand. By considering a class of neural ground costs whose Monge maps have a known form, we construct a differentiable Monge map estimator which can be optimized to be consistent with known information about an OT map. In doing so, we simultaneously learn both an OT map estimator and a corresponding adapted cost function. Through suitable choices of loss function, our method provides a general approach for incorporating prior information about the Monge map itself when learning adapted OT maps and cost functions.
format Preprint
id arxiv_https___arxiv_org_abs_2406_08399
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Differentiable Cost-Parameterized Monge Map Estimators
Howard, Samuel
Deligiannidis, George
Rebeschini, Patrick
Thornton, James
Machine Learning
Within the field of optimal transport (OT), the choice of ground cost is crucial to ensuring that the optimality of a transport map corresponds to usefulness in real-world applications. It is therefore desirable to use known information to tailor cost functions and hence learn OT maps which are adapted to the problem at hand. By considering a class of neural ground costs whose Monge maps have a known form, we construct a differentiable Monge map estimator which can be optimized to be consistent with known information about an OT map. In doing so, we simultaneously learn both an OT map estimator and a corresponding adapted cost function. Through suitable choices of loss function, our method provides a general approach for incorporating prior information about the Monge map itself when learning adapted OT maps and cost functions.
title Differentiable Cost-Parameterized Monge Map Estimators
topic Machine Learning
url https://arxiv.org/abs/2406.08399