Intrinsic Dimensionality Estimation within Tight Localities - Inria - Institut national de recherche en sciences et technologies du numérique
Conference Papers Year : 2019

Intrinsic Dimensionality Estimation within Tight Localities

Abstract

Accurate estimation of Intrinsic Dimensionality (ID) is of crucial importance in many data mining and machine learning tasks, including dimensionality reduction, outlier detection, similarity search and subspace clustering. However, since their convergence generally requires sample sizes (that is, neighborhood sizes) on the order of hundreds of points, existing ID estimation methods may have only limited usefulness for applications in which the data consists of many natural groups of small size. In this paper, we propose a local ID estimation strategy stable even for ‘tight’ localities consisting of as few as 20 sample points. The estimator applies MLE techniques over all available pairwise distances among the members of the sample, based on a recent extreme-value-theoretic model of intrinsic dimensionality, the Local Intrinsic Dimension (LID). Our experimental results show that our proposed estimation technique can achieve notably smaller variance, while maintaining comparable levels of bias, at much smaller sample sizes than state-of-the-art estimators.
Fichier principal
Vignette du fichier
tight.pdf (1.1 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-02125331 , version 1 (08-12-2020)

Licence

Identifiers

Cite

Laurent Amsaleg, Oussama Chelly, Michael E Houle, Ken-Ichi Kawarabayashi, Miloš Radovanović, et al.. Intrinsic Dimensionality Estimation within Tight Localities. 2019 SIAM International conference on Data Mining, May 2019, Calgary (Alberta), Canada. pp.181-189, ⟨10.1137/1.9781611975673.21⟩. ⟨hal-02125331⟩
202 View
172 Download

Altmetric

Share

More