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.

Aggregation via Empirical risk minimization

dc.contributor.authorMendelson, Shahar
dc.contributor.authorLecue, Guillaume
dc.date.accessioned2015-12-08T22:40:21Z
dc.date.available2015-12-08T22:40:21Z
dc.date.issued2009
dc.date.updated2015-12-08T10:22:50Z
dc.description.abstractGiven a finite set F of estimators, the problem of aggregation is to construct a new estimator whose risk is as close as possible to the risk of the best estimator in F. It was conjectured that empirical minimization performed in the convex hull of F is an optimal aggregation method, but we show that this conjecture is false. Despite that, we prove that empirical minimization in the convex hull of a well chosen, empirically determined subset of F is an optimal aggregation method.
dc.identifier.issn0178-8051
dc.identifier.urihttp://hdl.handle.net/1885/36461
dc.publisherSpringer
dc.sourceProbability Theory and Related Fields
dc.titleAggregation via Empirical risk minimization
dc.typeJournal article
local.bibliographicCitation.lastpage613
local.bibliographicCitation.startpage591
local.contributor.affiliationMendelson, Shahar, College of Physical and Mathematical Sciences, ANU
local.contributor.affiliationLecue, Guillaume, College of Physical and Mathematical Sciences, ANU
local.contributor.authoruidMendelson, Shahar, u4011413
local.contributor.authoruidLecue, Guillaume, u4762074
local.description.notesImported from ARIES
local.identifier.absfor010101 - Algebra and Number Theory
local.identifier.ariespublicationu9209279xPUB136
local.identifier.citationvolume145
local.identifier.doi10.1007/s00440-008-0180-8
local.identifier.scopusID2-s2.0-70350012166
local.type.statusPublished Version

Downloads

abcd