Online allocation with risk information

Shigeaki Harada, Eiji Takimoto, Akira Maruoka

Research output: Contribution to journalArticle

Abstract

We consider the problem of dynamically apportioning resources among a set of options in a worst-case online framework. The model we investigate is a generalization of the well studied online learning model. In particular, we allow the learner to see as additional information how high the risk of each option is. This assumption is natural in many applications like horse-race betting, where gamblers know odds for all options before placing bets. We apply Vovk's Aggregating Algorithm to this problem and give a tight performance bound. The results support our intuition that it is safe to bet more on low-risk options. Surprisingly, the loss bound of the algorithm does not depend on the values of relatively small risks.

Original languageEnglish
Pages (from-to)2340-2347
Number of pages8
JournalIEICE Transactions on Information and Systems
VolumeE89-D
Issue number8
DOIs
Publication statusPublished - Jan 1 2006

All Science Journal Classification (ASJC) codes

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering
  • Artificial Intelligence

Cite this

Online allocation with risk information. / Harada, Shigeaki; Takimoto, Eiji; Maruoka, Akira.

In: IEICE Transactions on Information and Systems, Vol. E89-D, No. 8, 01.01.2006, p. 2340-2347.

Research output: Contribution to journalArticle

Harada, Shigeaki ; Takimoto, Eiji ; Maruoka, Akira. / Online allocation with risk information. In: IEICE Transactions on Information and Systems. 2006 ; Vol. E89-D, No. 8. pp. 2340-2347.
@article{4541d413637d4cfa97550d071224630f,
title = "Online allocation with risk information",
abstract = "We consider the problem of dynamically apportioning resources among a set of options in a worst-case online framework. The model we investigate is a generalization of the well studied online learning model. In particular, we allow the learner to see as additional information how high the risk of each option is. This assumption is natural in many applications like horse-race betting, where gamblers know odds for all options before placing bets. We apply Vovk's Aggregating Algorithm to this problem and give a tight performance bound. The results support our intuition that it is safe to bet more on low-risk options. Surprisingly, the loss bound of the algorithm does not depend on the values of relatively small risks.",
author = "Shigeaki Harada and Eiji Takimoto and Akira Maruoka",
year = "2006",
month = "1",
day = "1",
doi = "10.1093/ietisy/e89-d.8.2340",
language = "English",
volume = "E89-D",
pages = "2340--2347",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "一般社団法人電子情報通信学会",
number = "8",

}

TY - JOUR

T1 - Online allocation with risk information

AU - Harada, Shigeaki

AU - Takimoto, Eiji

AU - Maruoka, Akira

PY - 2006/1/1

Y1 - 2006/1/1

N2 - We consider the problem of dynamically apportioning resources among a set of options in a worst-case online framework. The model we investigate is a generalization of the well studied online learning model. In particular, we allow the learner to see as additional information how high the risk of each option is. This assumption is natural in many applications like horse-race betting, where gamblers know odds for all options before placing bets. We apply Vovk's Aggregating Algorithm to this problem and give a tight performance bound. The results support our intuition that it is safe to bet more on low-risk options. Surprisingly, the loss bound of the algorithm does not depend on the values of relatively small risks.

AB - We consider the problem of dynamically apportioning resources among a set of options in a worst-case online framework. The model we investigate is a generalization of the well studied online learning model. In particular, we allow the learner to see as additional information how high the risk of each option is. This assumption is natural in many applications like horse-race betting, where gamblers know odds for all options before placing bets. We apply Vovk's Aggregating Algorithm to this problem and give a tight performance bound. The results support our intuition that it is safe to bet more on low-risk options. Surprisingly, the loss bound of the algorithm does not depend on the values of relatively small risks.

UR - http://www.scopus.com/inward/record.url?scp=33747870420&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33747870420&partnerID=8YFLogxK

U2 - 10.1093/ietisy/e89-d.8.2340

DO - 10.1093/ietisy/e89-d.8.2340

M3 - Article

VL - E89-D

SP - 2340

EP - 2347

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 8

ER -