Robust Barycenter Estimation using Semi-Unbalanced Neural Optimal Transport

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gazdieva, Milena, Choi, Jaemoo, Kolesov, Alexander, Choi, Jaewoong, Mokrov, Petr, Korotin, Alexander
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908316026798080
author Gazdieva, Milena
Choi, Jaemoo
Kolesov, Alexander
Choi, Jaewoong
Mokrov, Petr
Korotin, Alexander
author_facet Gazdieva, Milena
Choi, Jaemoo
Kolesov, Alexander
Choi, Jaewoong
Mokrov, Petr
Korotin, Alexander
contents Aggregating data from multiple sources can be formalized as an Optimal Transport (OT) barycenter problem, which seeks to compute the average of probability distributions with respect to OT discrepancies. However, in real-world scenarios, the presence of outliers and noise in the data measures can significantly hinder the performance of traditional statistical methods for estimating OT barycenters. To address this issue, we propose a novel scalable approach for estimating the robust continuous barycenter, leveraging the dual formulation of the (semi-)unbalanced OT problem. To the best of our knowledge, this paper is the first attempt to develop an algorithm for robust barycenters under the continuous distribution setup. Our method is framed as a min-max optimization problem and is adaptable to general cost functions. We rigorously establish the theoretical underpinnings of the proposed method and demonstrate its robustness to outliers and class imbalance through a number of illustrative experiments. Our source code is publicly available at https://github.com/milenagazdieva/U-NOTBarycenters.
format Preprint
id arxiv_https___arxiv_org_abs_2410_03974
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Robust Barycenter Estimation using Semi-Unbalanced Neural Optimal Transport
Gazdieva, Milena
Choi, Jaemoo
Kolesov, Alexander
Choi, Jaewoong
Mokrov, Petr
Korotin, Alexander
Machine Learning
Artificial Intelligence
Aggregating data from multiple sources can be formalized as an Optimal Transport (OT) barycenter problem, which seeks to compute the average of probability distributions with respect to OT discrepancies. However, in real-world scenarios, the presence of outliers and noise in the data measures can significantly hinder the performance of traditional statistical methods for estimating OT barycenters. To address this issue, we propose a novel scalable approach for estimating the robust continuous barycenter, leveraging the dual formulation of the (semi-)unbalanced OT problem. To the best of our knowledge, this paper is the first attempt to develop an algorithm for robust barycenters under the continuous distribution setup. Our method is framed as a min-max optimization problem and is adaptable to general cost functions. We rigorously establish the theoretical underpinnings of the proposed method and demonstrate its robustness to outliers and class imbalance through a number of illustrative experiments. Our source code is publicly available at https://github.com/milenagazdieva/U-NOTBarycenters.
title Robust Barycenter Estimation using Semi-Unbalanced Neural Optimal Transport
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2410.03974