Cases & Studies in Internet Gambling
- date : 2015-05-20 01:10|hit : 377
-
- Article; Proceedings Paper] Online allocation with risk information
-
DocNo of ILP: 5365
Doc. Type: Article; Proceedings Paper
Title: Online allocation with risk information
Authors: Harada, S; Takimoto, E; Maruoka, A
Full Name of Authors: Harada, S; Takimoto, E; Maruoka, A
Keywords by Author:
Keywords Plus: EXPERT ADVICE; PREDICTION
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 the Aggregating Algorithm to this problem and give a tight performance bound. The results support our intuition that we should bet more on low-risk options. Surprisingly, however, the Hedge Algorithm without seeing risk information performs nearly as well as the Aggregating Algorithm. So the risk information does not help much. Moreover, the loss bound does not depend on the values of relatively small risks.
Cate of OECD: Computer and information sciences
Year of Publication: 2005
Business Area: gamble
Detail Business: gamble
Country: Germany
Study Area: prediction, prediction, software, algorithm, gambler, risk
Name of Journal: ALGORITHMIC LEARNING THEORY
Language: English
Country of Authors: Tohoku Univ, Grad Sch Informat Sci, Sendai, Miyagi 9808579, Japan
Press Adress: Takimoto, E (reprint author), Tohoku Univ, Grad Sch Informat Sci, Sendai, Miyagi 9808579, Japan.
Email Address: sig@maruoka.ecei.tohoku.ac.jp; t2@maruoka.ecei.tohoku.ac.jp; maruoka@maruoka.ecei.tohoku.ac.jp
Citaion:
Funding:
Lists of Citation: Cesa-Bianchi N, 1999, ANN STAT, V27, P1865; Freund Y, 1997, J COMPUT SYST SCI, V55, P119, DOI 10.1006/jcss.1997.1504; HANNAN J, 1957, APPROXIMATION BAYES, V3; Hutter M, 2004, LECT NOTES ARTIF INT, V3244, P279; Kalai A, 2003, LECT NOTES ARTIF INT, V2777, P26, DOI 10.1007/978-3-540-45167-9_4; LITTLESTONE N, 1994, INFORM COMPUT, V108, P212, DOI 10.1006/inco.1994.1009; Takimoto E., 2003, J MACHINE LEARNING R, V4, P773; Vovk V, 1998, J COMPUT SYST SCI, V56, P153, DOI 10.1006/jcss.1997.1556
Number of Citaion: 8
Publication: SPRINGER-VERLAG BERLIN
City of Publication: BERLIN
Address of Publication: HEIDELBERGER PLATZ 3, D-14197 BERLIN, GERMANY
ISSN: 0302-9743
29-Character Source Abbreviation: LECT NOTES ARTIF INT
ISO Source Abbreviation:
Volume: 3734
Version:
Start of File: 343
End of File: 355
DOI:
Number of Pages: 13
Web of Science Category: Computer Science, Artificial Intelligence; Computer Science, Theory & Methods; Mathematics, Applied
Subject Category: Computer Science; Mathematics
Document Delivery Number: BDH68
Unique Article Identifier: WOS:000233583800026
[이 게시물은 HyeJung Mo…님에 의해 2015-05-20 14:44:04 GAMBLING에서 이동 됨]
- reply : 0
-
- list
-
- prev
- next