Saved in:
Bibliographic Details
Main Author: Kravtsova, Natalia
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.06525
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911428983652352
author Kravtsova, Natalia
author_facet Kravtsova, Natalia
contents This note addresses computational difficulty of the Gromov-Wasserstein distance frequently mentioned in the literature. We provide details on the structure of the Gromov-Wasserstein distance optimization problem that show its non-convex quadratic nature for any instance of an input data. We further illustrate the non-convexity of the problem with several explicit examples.
format Preprint
id arxiv_https___arxiv_org_abs_2408_06525
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Note on computational complexity of the Gromov-Wasserstein distance
Kravtsova, Natalia
Machine Learning
This note addresses computational difficulty of the Gromov-Wasserstein distance frequently mentioned in the literature. We provide details on the structure of the Gromov-Wasserstein distance optimization problem that show its non-convex quadratic nature for any instance of an input data. We further illustrate the non-convexity of the problem with several explicit examples.
title Note on computational complexity of the Gromov-Wasserstein distance
topic Machine Learning
url https://arxiv.org/abs/2408.06525