A Dual Basis Approach for Structured Robust Euclidean Distance Geometry

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kundu, Chandra, Tasissa, Abiy, Cai, HanQin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916756393558016
author Kundu, Chandra
Tasissa, Abiy
Cai, HanQin
author_facet Kundu, Chandra
Tasissa, Abiy
Cai, HanQin
contents Euclidean Distance Matrix (EDM), which consists of pairwise squared Euclidean distances of a given point configuration, finds many applications in modern machine learning. This paper considers the setting where only a set of anchor nodes is used to collect the distances between themselves and the rest. In the presence of potential outliers, it results in a structured partial observation on EDM with partial corruptions. Note that an EDM can be connected to a positive semi-definite Gram matrix via a non-orthogonal dual basis. Inspired by recent development of non-orthogonal dual basis in optimization, we propose a novel algorithmic framework, dubbed Robust Euclidean Distance Geometry via Dual Basis (RoDEoDB), for recovering the Euclidean distance geometry, i.e., the underlying point configuration. The exact recovery guarantees have been established in terms of both the Gram matrix and point configuration, under some mild conditions. Empirical experiments show superior performance of RoDEoDB on sensor localization and molecular conformation datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2505_18414
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Dual Basis Approach for Structured Robust Euclidean Distance Geometry
Kundu, Chandra
Tasissa, Abiy
Cai, HanQin
Machine Learning
Information Theory
Optimization and Control
Euclidean Distance Matrix (EDM), which consists of pairwise squared Euclidean distances of a given point configuration, finds many applications in modern machine learning. This paper considers the setting where only a set of anchor nodes is used to collect the distances between themselves and the rest. In the presence of potential outliers, it results in a structured partial observation on EDM with partial corruptions. Note that an EDM can be connected to a positive semi-definite Gram matrix via a non-orthogonal dual basis. Inspired by recent development of non-orthogonal dual basis in optimization, we propose a novel algorithmic framework, dubbed Robust Euclidean Distance Geometry via Dual Basis (RoDEoDB), for recovering the Euclidean distance geometry, i.e., the underlying point configuration. The exact recovery guarantees have been established in terms of both the Gram matrix and point configuration, under some mild conditions. Empirical experiments show superior performance of RoDEoDB on sensor localization and molecular conformation datasets.
title A Dual Basis Approach for Structured Robust Euclidean Distance Geometry
topic Machine Learning
Information Theory
Optimization and Control
url https://arxiv.org/abs/2505.18414