Generalized Watson distribution on the Hypersphere with applications to clustering

Maybank, Stephen and Liu, L. and Tau, D. (2023) Generalized Watson distribution on the Hypersphere with applications to clustering. Journal of Mathematical Imaging and Vision 65 , pp. 302-322. ISSN 0924-9907.

Abstract

A family of probability density functions (pdfs) is defined on the unit hypersphere S^{n}. The parameter space for the pdfs is G(d, n+1)xR_{>= 0}, for 1 <= d <= n, where G(d, n+1) is the Grassmannian of d dimensional linear subspaces in R^{n+1} and R}_{>= 0} is the range of values for a concentration parameter. This family of pdfs generalizes the Watson distribution on the sphere S^{2}. It is shown that the pdfs are tractable, in that i) a given pdf can be sampled efficiently, ii) the parameters of a pdf can be estimated using maximum likelihood, and iii) the Kullback-Leibler divergence and the Fisher-Rao metric on G(d, n+1)xR_{>= 0} have simple forms. A wide range of shapes of the pdfs can be obtained by varying d and the concentration parameter. The pdfs are used to model clusters of feature vectors on the hypersphere. The clusters are compared using the Kullback-Leibler divergences of the associated pdfs. Experiments with the mnist, Human Activity Recognition and Gas Sensor Array Drift datasets show that good results can be obtained from clustering algorithms based on the Kullback-Leibler divergence, even if the dimension n of the hypersphere is high.

Metadata

Statistics

DownloadsShow export options

Export as XMLJSONCSV

Activity Overview

6 month trend

24Downloads

6 month trend

70Hits

Additional statistics are available via IRStats2.

Archive Staff Only (login required)

Edit/View Item