Presentation 2005-03-18
Online Allocation with Risk Information
Shigeaki HARADA, Eiji TAKIMOTO, Akira MARUOKA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) 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 the Aggregating Algorithm to this problem and give a tight performance bound. The bound we give intuitively implies that the algorithm performs better when faced with options of various risks than when faced with options of the same risk.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) online learning / resource allocation / Hedge algorithm / aggregating algorithm
Paper # COMP2004-86
Date of Issue

Conference Information
Committee COMP
Conference Date 2005/3/11(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Theoretical Foundations of Computing (COMP)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Online Allocation with Risk Information
Sub Title (in English)
Keyword(1) online learning
Keyword(2) resource allocation
Keyword(3) Hedge algorithm
Keyword(4) aggregating algorithm
1st Author's Name Shigeaki HARADA
1st Author's Affiliation GSIS, Tohoku University()
2nd Author's Name Eiji TAKIMOTO
2nd Author's Affiliation GSIS, Tohoku University
3rd Author's Name Akira MARUOKA
3rd Author's Affiliation GSIS, Tohoku University
Date 2005-03-18
Paper # COMP2004-86
Volume (vol) vol.104
Number (no) 743
Page pp.pp.-
#Pages 6
Date of Issue