Title :
On Estimation of Quantiles for Pairwise Distances
Author :
Lolla, Sai Venu Gopal ; Hoberock, Lawrence L.
Author_Institution :
Sch. of Mech. & Aerosp. Eng., Oklahoma State Univ., Stillwater, OK, USA
Abstract :
This paper presents a novel method for estimating quantiles for pair wise distances. While the algorithm for computing pair wise distances for data is simple, the computation times as well as memory requirements grow quadratically with the size of the input dataset, making a naive implementation undesirable. In this paper, the performance of the proposed method is compared to the performances of a naive implementation, an estimation method due to Weide, and a selection method due to Mizoguchi and Johnson.
Keywords :
data analysis; computing pair wise distances; estimating quantiles; memory requirements; naive implementation; pairwise distances; selection method; Accuracy; Aerospace engineering; Approximation methods; Arrays; Estimation; Histograms; Memory management; pairwise distance; quantile estimation;
Conference_Titel :
Machine Learning and Applications (ICMLA), 2010 Ninth International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
978-1-4244-9211-4
DOI :
10.1109/ICMLA.2010.124
