Linear Optimal Partial Transport Embedding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bai, Yikun, Medri, Ivan, Martin, Rocio Diaz, Khan, Rana Muhammad Shahroz, Kolouri, Soheil
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929324625494016
author Bai, Yikun
Medri, Ivan
Martin, Rocio Diaz
Khan, Rana Muhammad Shahroz
Kolouri, Soheil
author_facet Bai, Yikun
Medri, Ivan
Martin, Rocio Diaz
Khan, Rana Muhammad Shahroz
Kolouri, Soheil
contents Optimal transport (OT) has gained popularity due to its various applications in fields such as machine learning, statistics, and signal processing. However, the balanced mass requirement limits its performance in practical problems. To address these limitations, variants of the OT problem, including unbalanced OT, Optimal partial transport (OPT), and Hellinger Kantorovich (HK), have been proposed. In this paper, we propose the Linear optimal partial transport (LOPT) embedding, which extends the (local) linearization technique on OT and HK to the OPT problem. The proposed embedding allows for faster computation of OPT distance between pairs of positive measures. Besides our theoretical contributions, we demonstrate the LOPT embedding technique in point-cloud interpolation and PCA analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2302_03232
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Linear Optimal Partial Transport Embedding
Bai, Yikun
Medri, Ivan
Martin, Rocio Diaz
Khan, Rana Muhammad Shahroz
Kolouri, Soheil
Machine Learning
Optimization and Control
Optimal transport (OT) has gained popularity due to its various applications in fields such as machine learning, statistics, and signal processing. However, the balanced mass requirement limits its performance in practical problems. To address these limitations, variants of the OT problem, including unbalanced OT, Optimal partial transport (OPT), and Hellinger Kantorovich (HK), have been proposed. In this paper, we propose the Linear optimal partial transport (LOPT) embedding, which extends the (local) linearization technique on OT and HK to the OPT problem. The proposed embedding allows for faster computation of OPT distance between pairs of positive measures. Besides our theoretical contributions, we demonstrate the LOPT embedding technique in point-cloud interpolation and PCA analysis.
title Linear Optimal Partial Transport Embedding
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2302.03232