$β$-integrated local depth and corresponding partitioned local depth representation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Siyi, Leblanc, Alexandre, McNicholas, Paul D.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918067254067200
author Wang, Siyi
Leblanc, Alexandre
McNicholas, Paul D.
author_facet Wang, Siyi
Leblanc, Alexandre
McNicholas, Paul D.
contents A novel local depth definition, $β$-integrated local depth ($β$-ILD), is proposed as a generalization of the local depth introduced by Paindaveine and Van Bever \cite{paindaveine2013depth}, designed to quantify the local centrality of data points. $β$-ILD inherits desirable properties from global data depth and remains robust across varying locality levels. A partitioning approach for $β$-ILD is introduced, leading to the construction of a matrix that quantifies the contribution of one point to another's local depth, providing a new interpretable measure of local centrality. These concepts are applied to classification and outlier detection tasks, demonstrating significant improvements in the performance of depth-based algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14108
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle $β$-integrated local depth and corresponding partitioned local depth representation
Wang, Siyi
Leblanc, Alexandre
McNicholas, Paul D.
Statistics Theory
Methodology
A novel local depth definition, $β$-integrated local depth ($β$-ILD), is proposed as a generalization of the local depth introduced by Paindaveine and Van Bever \cite{paindaveine2013depth}, designed to quantify the local centrality of data points. $β$-ILD inherits desirable properties from global data depth and remains robust across varying locality levels. A partitioning approach for $β$-ILD is introduced, leading to the construction of a matrix that quantifies the contribution of one point to another's local depth, providing a new interpretable measure of local centrality. These concepts are applied to classification and outlier detection tasks, demonstrating significant improvements in the performance of depth-based algorithms.
title $β$-integrated local depth and corresponding partitioned local depth representation
topic Statistics Theory
Methodology
url https://arxiv.org/abs/2506.14108