Multidimensional scaling with very large datasets - Archive ouverte HAL Access content directly
Journal Articles Journal of Computational and Graphical Statistics Year : 2018

Multidimensional scaling with very large datasets

(1)
1

Abstract

Multidimensional scaling has a wide range of applications when observations are not continuous but it is possible to define a distance (or dissimilarity) among them. However, standard implementations are limited when analyzing very large data sets because they rely on eigendecomposition of the full distance matrix and require very long computing times and large quantities of memory. Here, a new approach is developed based on projection of the observations in a space defined by a subset of the full data set. The method is easily implemented. A simulation study showed that its performance are satisfactory in different situations and can be run in a short time when the standard method takes a very long time or cannot be run because of memory requirements.
Fichier principal
Vignette du fichier
Paradis_2018_JCGS.pdf (167.32 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

ird-01920130 , version 1 (11-07-2019)

Identifiers

Cite

Emmanuel Paradis. Multidimensional scaling with very large datasets. Journal of Computational and Graphical Statistics, 2018, pp.1 - 5. ⟨10.1080/10618600.2018.1470001⟩. ⟨ird-01920130⟩
151 View
875 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More