CaltechAUTHORS
  A Caltech Library Service

Massively-parallel best subset selection for ordinary least-squares regression

Gieseke, Fabian and Polsterer, Kai Lars and Mahabal, Ashish and Igel, Christian and Heskes, Tom (2017) Massively-parallel best subset selection for ordinary least-squares regression. In: 2017 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE , Piscataway, NJ, pp. 1-8. ISBN 978-1-5386-2726-6. http://resolver.caltech.edu/CaltechAUTHORS:20180216-161024980

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20180216-161024980

Abstract

Selecting an optimal subset of k out of d features for linear regression models given n training instances is often considered intractable for feature spaces with hundreds or thousands of dimensions. We propose an efficient massively-parallel implementation for selecting such optimal feature subsets in a brute-force fashion for small k. By exploiting the enormous compute power provided by modern parallel devices such as graphics processing units, it can deal with thousands of input dimensions even using standard commodity hardware only. We evaluate the practical runtime using artificial datasets and sketch the applicability of our framework in the context of astronomy.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.1109/SSCI.2017.8285225DOIArticle
http://ieeexplore.ieee.org/document/8285225PublisherArticle
Additional Information:© 2017 IEEE. Fabian Gieseke acknowledges support from the Danish Industry Foundation through the Industrial Data Analysis Service (IDAS) and Christian Igel acknowledges support from the Innovation Fund Denmark through the Danish Center for Big Data Analytics Driven Innovation (DABAI).
Funders:
Funding AgencyGrant Number
Danish Industry FoundationUNSPECIFIED
Danish Center for Big Data Analytics Driven Innovation (DABAI)UNSPECIFIED
Subject Keywords:Computational modeling, Runtime, Graphics processing units, Task analysis, Instruction sets, Training, Optimization
Record Number:CaltechAUTHORS:20180216-161024980
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20180216-161024980
Official Citation:F. Gieseke, K. L. Polsterer, A. Mahabal, C. Igel and T. Heskes, "Massively-parallel best subset selection for ordinary least-squares regression," 2017 IEEE Symposium Series on Computational Intelligence (SSCI), Honolulu, HI, USA, 2017, pp. 1-8. doi: 10.1109/SSCI.2017.8285225. URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8285225&isnumber=8280782
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:84875
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:22 Feb 2018 03:38
Last Modified:22 Feb 2018 03:38

Repository Staff Only: item control page