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

Alexey Chernov
, Fedor Zhdanov

University of Bedfordshire

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

22 Citations (Scopus)

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	nan
Publisher	Springer
ISBN (Electronic)	978-3-642-16107-0
ISBN (Print)	978-3-642-16107-0
DOIs	https://doi.org/10.1007/978-3-642-16108-7_22
Publication status	Published - 1 Jan 2010
Event	Algorithmic Learning Theory 2010 - Duration: 1 Jan 2010 → …

Conference

Conference	Algorithmic Learning Theory 2010
Period	1/01/10 → …
Other	Algorithmic Learning Theory 2010

Keywords

prediction

Access to Document

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

http://link.springer.com/chapter/10.1007%252F978-3-642-16108-7_22

Handle.net

Persistent link

Cite this

@inproceedings{6590229d21f64da89de8b77fde2e499c,

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",

keywords = "prediction",

author = "Alexey Chernov and Fedor Zhdanov",

year = "2010",

month = jan,

day = "1",

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

language = "English",

isbn = "978-3-642-16107-0",

booktitle = "nan",

publisher = "Springer",

address = "Germany",

note = "Algorithmic Learning Theory 2010 ; Conference date: 01-01-2010",

}

TY - GEN

T1 - Prediction with expert advice under discounted loss

AU - Chernov, Alexey

AU - Zhdanov, Fedor

PY - 2010/1/1

Y1 - 2010/1/1

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

KW - prediction

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

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

M3 - Conference contribution

SN - 978-3-642-16107-0

BT - nan

PB - Springer

T2 - Algorithmic Learning Theory 2010

Y2 - 1 January 2010

ER -

Prediction with expert advice under discounted loss

Abstract

Conference

Keywords

Access to Document

Handle.net

Fingerprint

Cite this