MAINTENANCE EN COURS / SITE UNDER MAINTENANCE

Une opération de maintenance est en cours: les résultats de recherches et les exportations peuvent être incohérent.
Site under maintenance: search & exportation results could be inconsistent.
 

Multiscale stochastic neighbor embedding: Towards parameter-free dimensionality reduction

Lee, John;Peluffo Ordoñez, Diego Hernan;Verleysen, Michel
(2014) 2014 European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2014) — Location: Bruges (Belgium) (23.April.2014)

Files

Multiscalestochasticneighborembedding-Towardsparameter-freedimensionalityreduction.pdf
  • Restricted Access
  • Adobe PDF
  • 1.94 MB
Request a copy

Details

Authors
Abstract
Stochastic neighbor embedding (SNE) is a method of dimensionality reduction that involves softmax similarities measured between all pairs of data points. To build a suitable embedding, SNE tries to reproduce in a low-dimensional space the similarities that are observed in the high-dimensional data space. Previous work has investigated the immunity of such similarities to norm concentration, as well as enhanced cost functions. This paper proposes an additional refinement, in the form of multiscale similarities, namely averages of softmax ratios with decreasing bandwidths. The objective is to maximize the embedding quality at all scales, with a better preservation of both local and global neighborhoods, and also to exempt the user from having to fix a scale arbitrarily. Experiments on several data sets show that this multiscale version of SNE, combined with an appropriate cost function (sum of Jensen-Shannon divergences), outperforms all previous variants of SNE.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

Lee, J., Peluffo Ordoñez, D. H., & Verleysen, M. (2014). Multiscale stochastic neighbor embedding: Towards parameter-free dimensionality reduction. Proceedings of ESANN 2014, 177-182. https://hdl.handle.net/2078.5/253837