A tutorial on the cross-entropy method

被引：2244
作者：
De Boer, PT
Kroese, DP
Mannor, S
Rubinstein, RY
机构：
[1] Univ Twente, Dept Elect Engn Math & Comp Sci, NL-7500 AE Enschede, Netherlands
[2] Univ Queensland, Dept Math, Brisbane, Qld 4072, Australia
[3] McGill Univ, Dept Elect & Comp Engn, Montreal, PQ, Canada
[4] Technion Israel Inst Technol, Dept Ind Engn, IL-32000 Haifa, Israel
来源：
ANNALS OF OPERATIONS RESEARCH | 2005年 / 134卷 / 01期
基金：
以色列科学基金会;
关键词：
cross-entropy method; Monte-Carlo simulation; randomized optimization; machine learning; rare events;
D O I：
10.1007/s10479-005-5724-z
中图分类号：
C93 [管理学]; O22 [运筹学];
学科分类号：
070105 ; 12 ; 1201 ; 1202 ; 120202 ;
摘要：
The cross-entropy (CE) method is a new generic approach to combinatorial and multi-extremal optimization and rare event simulation. The purpose of this tutorial is to give a gentle introduction to the CE method. We present the CE methodology, the basic algorithm and its modifications, and discuss applications in combinatorial optimization and machine learning.
引用
收藏
页码：19 / 67
页数：49
相关论文
共 50 条
[1]  
Aarts E., 1989, Wiley-Interscience Series in Discrete Mathematics and Optimization
[2]  
Alon G., 2005, ANN OPER RES, V134, P19
[3]  
[Anonymous], 1989, GENETIC ALGORITHM SE
[4]  
[Anonymous], 1979, Computers and Intractablity: A Guide to the Theoryof NP-Completeness
[5]  
ASMUSSEN S, 2005, IN PRESS STOCHASTIC, V21
[6]   NEURONLIKE ADAPTIVE ELEMENTS THAT CAN SOLVE DIFFICULT LEARNING CONTROL-PROBLEMS [J].
BARTO, AG ;
SUTTON, RS ;
ANDERSON, CW .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1983, 13 (05) :834-846
[7]  
BARTON AG, 1998, REINFORCEMENT LEARNI
[8]   Experiments with infinite-horizon, policy-gradient estimation [J].
Baxter, J ;
Bartlett, PL ;
Weaver, L .
JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH, 2001, 15 :351-381
[9]  
Bertsekas DP, 2012, DYNAMIC PROGRAMMING, V2
[10]  
BERTSEKAS DP, 1995, NEURODYNAMIC PROGRAM
12345