Online Allocation with Risk Information

Shigeaki HARADA; Eiji TAKIMOTO; Akira MARUOKA

doi:10.1093/ietisy/e89-d.8.2340

Online Allocation with Risk Information

Shigeaki HARADA, Eiji TAKIMOTO, Akira MARUOKA

Full Text Views

0

Share
Cite this

Summary :

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.

Publication: IEICE TRANSACTIONS on Information Vol.E89-D No.8 pp.2340-2347

Publication Date: 2006/08/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1093/ietisy/e89-d.8.2340

Type of Manuscript: Special Section INVITED PAPER (Special Section on Invited Papers from New Horizons in Computing)

Category

Cite this

Copy

Shigeaki HARADA, Eiji TAKIMOTO, Akira MARUOKA, "Online Allocation with Risk Information" in IEICE TRANSACTIONS on Information, vol. E89-D, no. 8, pp. 2340-2347, August 2006, doi: 10.1093/ietisy/e89-d.8.2340.
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.
URL: https://globals.ieice.org/en_transactions/information/10.1093/ietisy/e89-d.8.2340/_p

Copy

@ARTICLE{e89-d_8_2340,
author={Shigeaki HARADA, Eiji TAKIMOTO, Akira MARUOKA, },
journal={IEICE TRANSACTIONS on Information},
title={Online Allocation with Risk Information},
year={2006},
volume={E89-D},
number={8},
pages={2340-2347},
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.},
keywords={},
doi={10.1093/ietisy/e89-d.8.2340},
ISSN={1745-1361},
month={August},}

Copy

TY - JOUR
TI - Online Allocation with Risk Information
T2 - IEICE TRANSACTIONS on Information
SP - 2340
EP - 2347
AU - Shigeaki HARADA
AU - Eiji TAKIMOTO
AU - Akira MARUOKA
PY - 2006
DO - 10.1093/ietisy/e89-d.8.2340
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E89-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2006
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.
ER -