DMCA
On Low Distortion Embeddings of Statistical Distance Measures into Low Dimensional Spaces ∗ (909)
| Citations: | 2 - 0 self |
BibTeX
@MISC{Bhattacharya909onlow,
author = {Arnab Bhattacharya and Purushottam Kar and Manjish Pal},
title = {On Low Distortion Embeddings of Statistical Distance Measures into Low Dimensional Spaces ∗},
year = {909}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Statistical distance measures have found wide applicability in information retrieval tasks that typically involve high dimensional datasets. In order to reduce the storage space and ensure efficient performance of queries, dimensionality reduction while preserving the inter-point similarity is highly desirable. In this paper, we investigate various statistical distance measures from the point of view of discovering low distortion embeddings into low-dimensional spaces. More specifically, we consider the Mahalanobis distance measure, the Bhattacharyya class of divergences and the Kullback-Leibler divergence. We present a dimensionality reduction method based on the Johnson-Lindenstrauss Lemma for the Mahalanobis measure that achieves arbitrarily low distortion. By using the Johnson-Lindenstrauss Lemma again, we further demonstrate that the Bhattacharyya distance admits dimensionality reduction with arbitrarily low additive error. We also examine the question of embeddability into metric spaces for these distance measures due to the availability of efficient indexing schemes on metric spaces. We provide explicit constructions of point sets under the Bhattacharyya and the Kullback-Leibler divergences whose embeddings into any metric space incur arbitrarily large distortions. We show that the lower bound presented for Bhattacharyya distance is nearly tight by providing an embedding that approaches the lower bound for relatively small dimensional datasets. 1
Keyphrases
statistical distance measure low distortion embeddings metric space low dimensional space johnson-lindenstrauss lemma kullback-leibler divergence wide applicability inter-point similarity dimensionality reduction method mahalanobis measure point set information retrieval task bhattacharyya distance admits dimensionality reduction dimensionality reduction various statistical distance measure storage space bhattacharyya distance low distortion mahalanobis distance measure explicit construction low-dimensional space efficient performance low additive error large distortion bhattacharyya class distance measure small dimensional datasets high dimensional datasets
