FEATURE ELIMINATION IN KERNEL MACHINES IN MODERATELY HIGH DIMENSIONS.

TitleFEATURE ELIMINATION IN KERNEL MACHINES IN MODERATELY HIGH DIMENSIONS.
Publication TypeJournal Article
Year of Publication2019
AuthorsDasgupta, Sayan, Yair Goldberg, and Michael R. Kosorok
JournalAnn Stat
Volume47
Issue1
Pagination497-526
Date Published2019 Feb
ISSN0090-5364
Abstract

We develop an approach for feature elimination in statistical learning with kernel machines, based on recursive elimination of features. We present theoretical properties of this method and show that it is uniformly consistent in finding the correct feature space under certain generalized assumptions. We present a few case studies to show that the assumptions are met in most practical situations and present simulation results to demonstrate performance of the proposed approach.

DOI10.1214/18-AOS1696
Alternate JournalAnn Stat
Original PublicationFeature elimination in kernel machines in moderately high dimensions.
PubMed ID30559548
PubMed Central IDPMC6294291
Grant ListP01 CA142538 / CA / NCI NIH HHS / United States