Multidimensional scaling with very large datasets

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.
Complete list of metadatas

Cited literature [13 references]  Display  Hide  Download

http://hal.ird.fr/ird-01920130
Contributor : Emmanuel Paradis <>
Submitted on : Thursday, July 11, 2019 - 8:48:52 AM
Last modification on : Friday, July 12, 2019 - 1:18:50 AM

File

Paradis_2018_JCGS.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

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

Share

Metrics

Record views

111

Files downloads

26