Prediction with Expert Advice under Discounted Loss

Alexey Chernov; Fedor Zhdanov

doi:10.1007/978-3-642-16108-7_22

Prediction with Expert Advice under Discounted Loss

University of Brighton

Research output: Chapter in Book/Conference proceeding with ISSN or ISBN › Conference contribution with ISSN or ISBN › peer-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 language	English
Title of host publication	21st International Conference, ALT 2010
Place of Publication	Berlin
Publisher	Springer
Pages	255-269
Number of pages	15
Volume	6331
DOIs	https://doi.org/10.1007/978-3-642-16108-7_22
Publication status	Published - 31 Dec 2010
Event	21st International Conference, ALT 2010 - Canberra, Australia, October 6-8, 2010 Duration: 31 Dec 2010 → …

Publication series

Name	Lecture Notes in Computer Science

Conference

Conference	21st International Conference, ALT 2010
Period	31/12/10 → …

Bibliographical note

Access to Document

10.1007/978-3-642-16108-7_22Licence: Unspecified

Cite this

@inproceedings{f5e0227001e648c0a3eb12c381bba454,

title = "Prediction with Expert Advice under Discounted Loss",

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.",

author = "Alexey Chernov and Fedor Zhdanov",

note = "{\textcopyright} Springer-Verlag Berlin Heidelberg 2010; 21st International Conference, ALT 2010 ; Conference date: 31-12-2010",

year = "2010",

month = dec,

day = "31",

doi = "10.1007/978-3-642-16108-7_22",

language = "English",

volume = "6331",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "255--269",

booktitle = "21st International Conference, ALT 2010",

}

TY - GEN

T1 - Prediction with Expert Advice under Discounted Loss

AU - Chernov, Alexey

AU - Zhdanov, Fedor

PY - 2010/12/31

Y1 - 2010/12/31

N2 - 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.

AB - 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.

U2 - 10.1007/978-3-642-16108-7_22

DO - 10.1007/978-3-642-16108-7_22

M3 - Conference contribution with ISSN or ISBN

VL - 6331

T3 - Lecture Notes in Computer Science

SP - 255

EP - 269

BT - 21st International Conference, ALT 2010

PB - Springer

CY - Berlin

T2 - 21st International Conference, ALT 2010

Y2 - 31 December 2010

ER -

Prediction with Expert Advice under Discounted Loss

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Fingerprint

Cite this