An asymptotically minimax kernel machine

Recently, a class of machine learning-inspired procedures, termed kernel machine methods, has been extensively developed in the statistical literature. In this note, we construct a so-called ‘adaptively minimax’ kernel machine. Such a construction highlights the limits on the interpretability of such kernel machines.

MoreLess

Year of publication:	2014
Authors:	Ghosh, Debashis
Published in:	Statistics & Probability Letters. - Elsevier, ISSN 0167-7152. - Vol. 95.2014, C, p. 33-38
Publisher:	Elsevier
Subject:	Data mining \| Decision theory \| Hard-thresholding \| Nonparametric regression \| Support vector machines

More details

Type of publication:	Article
Source:	RePEc - Research Papers in Economics

Persistent link: https://www.econbiz.de/10010939471