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
来源：
COMPUTER JOURNAL | 2006年 / 49卷 / 02期
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
[1]  
[Anonymous], J MACHINE LEARNING R
[2]   Adaptive and self-confident on-line learning algorithms [J].
Auer, P ;
Cesa-Bianchi, N ;
Gentile, C .
JOURNAL OF COMPUTER AND SYSTEM SCIENCES, 2002, 64 (01) :48-75
[3]   Finite-time analysis of the multiarmed bandit problem [J].
Auer, P ;
Cesa-Bianchi, N ;
Fischer, P .
MACHINE LEARNING, 2002, 47 (2-3) :235-256
[4]  
Auer P, 1995, AN S FDN CO, P322, DOI 10.1109/SFCS.1995.492488
[5]   Tracking the best disjunction [J].
Auer, P ;
Warmuth, MK .
MACHINE LEARNING, 1998, 32 (02) :127-150
[6]  
AWERBUCH B, 2005, 31 IEEE INFOCOM 2005
[7]  
Awerbuch B., 2004, Proceedings of the 36th ACM Symposiuim on Theory of Computing (STOC), P45
[8]  
Blackwell D., 1956, PAC J MATH, V6, P1, DOI [10.2140/pjm.1956.6.1, DOI 10.2140/PJM.1956.6.1]
[9]  
Bousquet O., 2003, Journal of Machine Learning Research, V3, P363, DOI 10.1162/153244303321897654
[10]   Minimizing regret with label efficient prediction [J].
Cesa-Bianchi, N ;
Lugosi, G ;
Stoltz, G .
IEEE TRANSACTIONS ON INFORMATION THEORY, 2005, 51 (06) :2152-2162
1234