Adaptive routing using expert advice

被引:10
作者
György, A
Ottucsák, G
机构
[1] Tech Univ Budapest, Dept Comp Sci & Informat Theory, H-1117 Budapest, Hungary
[2] Hungarian Acad Sci, Comp & Automat Res Inst, Informat Lab, H-1111 Budapest, Hungary
关键词
machine learning; network routing; adaptive routing;
D O I
10.1093/comjnl/bxh168
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Machine learning algorithms for combining expert advice in sequential decision problems are considered. The goal of these algorithms is to perform, for any behavior of the system, asymptotically as well as the best expert. We provide a survey of these algorithms and show how they can be used for adaptive routing in different packet switched networks.
引用
收藏
页码:180 / 189
页数:10
相关论文
共 32 条
[21]   Tracking the best expert [J].
Herbster, M ;
Warmuth, MK .
MACHINE LEARNING, 1998, 32 (02) :151-178
[22]   Efficient algorithms for online decision problems [J].
Kalai, A ;
Vempala, S .
LEARNING THEORY AND KERNEL MACHINES, 2003, 2777 :26-40
[23]   THE WEIGHTED MAJORITY ALGORITHM [J].
LITTLESTONE, N ;
WARMUTH, MK .
INFORMATION AND COMPUTATION, 1994, 108 (02) :212-261
[24]   Online geometric optimization in the bandit setting against an adaptive adversary [J].
McMahan, HB ;
Blum, A .
LEARNING THEORY, PROCEEDINGS, 2004, 3120 :109-123
[25]  
MOHRI M, 1998, 98121910TM ATT
[26]  
OTTUCSAK G, 2005, COMBINATION LABEL EF
[27]   SOME ASPECTS OF THE SEQUENTIAL DESIGN OF EXPERIMENTS [J].
ROBBINS, H .
BULLETIN OF THE AMERICAN MATHEMATICAL SOCIETY, 1952, 58 (05) :527-535
[28]  
Steenstrup M., 1995, ROUTING COMMUNICATIO
[29]  
TAKIMOTO E, 2002, LECT NOTES ARTIF INT, V2375, P74
[30]   A game of prediction with expert advice [J].
Vovk, V .
JOURNAL OF COMPUTER AND SYSTEM SCIENCES, 1998, 56 (02) :153-173