0000643: IMPLEMENTED: faster k-means clusterization (blocked, parallel)

Viewing Issue Simple Details [ Jump to Notes ]

[ View Advanced ] [ Issue History ] [ Print ]

Category

Severity

Reproducibility

Date Submitted

Last Update

0000643

[ALGLIB] Data analysis

feature

have not tried

2015-01-22 16:01

2018-01-25 18:07

Reporter

SergeyB

View Status

public

Assigned To

SergeyB

Priority

normal

Resolution

implemented

Status

resolved

Product Version

Summary

0000643: IMPLEMENTED: faster k-means clusterization (blocked, parallel)

Description

New incarnation of k-means is much faster than previous version due to several improvements:
* initialization algorithm was remastered - we can choose between random initialization, k-means++ (high-quality but slower and non-parallelizable), and "fast-greedy" algorithm which gives reasonably good results while being cache-efficient and parallelizable.
* main k-means iteration is now blocked and parallelized, which significantly improves performance on large-scale datasets

Additional Information

Programming language

Unspecified

Attached Files

Relationships

There are no notes attached to this issue.

Issue History
Date Modified	Username	Field	Change
2015-01-22 16:01	SergeyB	New Issue
2015-01-22 16:01	SergeyB	Status	new => assigned
2015-01-22 16:01	SergeyB	Assigned To	=> SergeyB
2015-01-22 16:01	SergeyB	Programming language	=> Unspecified
2015-01-22 16:01	SergeyB	Status	assigned => resolved
2015-01-22 16:01	SergeyB	Fixed in Version	=> Next release
2015-01-22 16:01	SergeyB	Resolution	open => implemented

Mantis 1.1.6[^]