Prediction with Expert Advice under Discounted Loss

Alexey Chernov, Fedor Zhdanov

Research output: Chapter in Book/Conference proceeding with ISSN or ISBNConference contribution with ISSN or ISBNpeer-review

Abstract

We study prediction with expert advice in the setting where the losses are accumulated with some discounting and the impact of old losses can gradually vanish. We generalize the Aggregating Algorithm and the Aggregating Algorithm for Regression, propose a new variant of exponentially weighted average algorithm, and prove bounds on the cumulative discounted loss.
Original languageEnglish
Title of host publication21st International Conference, ALT 2010
Place of PublicationBerlin
PublisherSpringer
Pages255-269
Number of pages15
Volume6331
DOIs
Publication statusPublished - 31 Dec 2010
Event21st International Conference, ALT 2010 - Canberra, Australia, October 6-8, 2010
Duration: 31 Dec 2010 → …

Publication series

NameLecture Notes in Computer Science

Conference

Conference21st International Conference, ALT 2010
Period31/12/10 → …

Bibliographical note

© Springer-Verlag Berlin Heidelberg 2010

Cite this