Data representation with optimal transport
Roc\'io D\'iaz Mart\'in, Ivan V. Medri, Gustavo Kunde Rohde
TL;DR
This paper reviews recent advances in using optimal transport for data representation, focusing on bijective transforms and metrics that improve data discrimination and signal analysis.
Contribution
It summarizes key developments in optimal transport applications, highlighting properties and main uses in data and signal processing.
Findings
Optimal transport enables effective bijective nonlinear transforms.
Transport metrics improve data discrimination capabilities.
Applications span various data analysis tasks.
Abstract
Optimal transport has been used to define bijective nonlinear transforms and different transport-related metrics for discriminating data and signals. Here we briefly describe the advances in this topic with the main applications and properties in each case.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsOptimization and Search Problems · Advanced Database Systems and Queries · Algorithms and Data Compression