Cultural advice

The Australian National University acknowledges, celebrates and pays our respects to the Ngunnawal and Ngambri people of the Canberra region and to all First Nations Australians on whose traditional lands we meet and work, and whose cultures are among the oldest continuing cultures in human history.

Aboriginal and Torres Strait Islander peoples are advised that ANU Library collections may include images, names, voices, and other representations of deceased persons.

Material in the collection may contain terms, language or views that reflect the period in which the item was created and may be considered inappropriate today.

Obtaining fast error rates in nonconvex situations

Date

Authors

Mendelson, Shahar

Publisher

Elsevier

Abstract

We show that under mild assumptions on the learning problem, one can obtain a fast error rate for every reasonable fixed target function even if the base class is not convex. To that end, we show that in such cases the excess loss class satisfies a Bernstein type condition.

Keywords

Keywords: Learning systems; (I ,J) conditions; Base class; Elsevier (CO); Error Rate (ER); excess losses; Learning problems; Nonconvex; Target functions; Error analysis Bernstein condition; Nearest point map; Nonconvex classes

URI

http://hdl.handle.net/1885/39068

Collections

ANU Research Publications

Source

Journal of Complexity

Type

Journal article

DOI

10.1016/j.jco.2007.09.001

Restricted until

2037-12-31

Downloads

File

Description

01_Mendelson_Obtaining_fast_error_rates_in_2008.pdf (264.15 KB)

abcd