[MAHOUT-645] Elkan distance optimization for VectorBenchmarks class

• Type: Improvement
• Status: Closed
• Priority: Minor
• Resolution: Fixed
• Affects Version/s: 0.4
• Fix Version/s: 0.5
• Component/s: classic
• Labels: centroid clustering elkan

Environment

Ubuntu Linux at Intel Core2 Duo P7450 @ 2.13GHz

• Assignee: Sean R. Owen
• Reporter: Gustavo Salazar Torres
• Due: 08/Apr/11
• Created: 31/Mar/11 13:40
• Updated: 31/Jan/24 22:14
• Resolved: 31/Mar/11 19:00

Description

Implementation of first lemma of Elkan's optimization:
Given three points x, b, c (where b and c are centroids):
d(b,c)>=2d(x.b) then d(x,c)>=d(x,b)
in which case we wouldn't need to calculate d(x,c). This is used to find the closest centroid for every point x.