skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Feature Clustering for Accelerating Parallel Coordinate Descent

Abstract

We demonstrate an approach for accelerating calculation of the regularization path for L1 sparse logistic regression problems. We show the benefit of feature clustering as a preconditioning step for parallel block-greedy coordinate descent algorithms.

Authors:
; ; ;
Publication Date:
Research Org.:
Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1111248
Report Number(s):
PNNL-SA-88340
400470000
DOE Contract Number:  
AC05-76RL01830
Resource Type:
Conference
Resource Relation:
Conference: Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems (NIPS 2012), December 3-6, 2012, Lake Tahoe, Nevada, 28-36
Country of Publication:
United States
Language:
English
Subject:
classification; sparse data; parallel computing; machine learning

Citation Formats

Scherrer, Chad, Tewari, Ambuj, Halappanavar, Mahantesh, and Haglin, David J. Feature Clustering for Accelerating Parallel Coordinate Descent. United States: N. p., 2012. Web.
Scherrer, Chad, Tewari, Ambuj, Halappanavar, Mahantesh, & Haglin, David J. Feature Clustering for Accelerating Parallel Coordinate Descent. United States.
Scherrer, Chad, Tewari, Ambuj, Halappanavar, Mahantesh, and Haglin, David J. Thu . "Feature Clustering for Accelerating Parallel Coordinate Descent". United States.
@article{osti_1111248,
title = {Feature Clustering for Accelerating Parallel Coordinate Descent},
author = {Scherrer, Chad and Tewari, Ambuj and Halappanavar, Mahantesh and Haglin, David J.},
abstractNote = {We demonstrate an approach for accelerating calculation of the regularization path for L1 sparse logistic regression problems. We show the benefit of feature clustering as a preconditioning step for parallel block-greedy coordinate descent algorithms.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2012},
month = {12}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share: