An improved averaged two-replication procedure with Latin hypercube sampling

被引：7
作者：
Bayraksan, Guezin [1 ]
机构：
[1] Ohio State Univ, Dept Integrated Syst Engn, Columbus, OH 43210 USA
来源：
OPERATIONS RESEARCH LETTERS | 2018年 / 46卷 / 02期
基金：
美国国家科学基金会;
关键词：
Stochastic optimization; Solution validation; Variance reduction; Latin hypercube sampling; Monte Carlo simulation; SOLUTION QUALITY; MODEL; PROBABILITY; UNCERTAINTY; VARIANCE; BIAS;
D O I：
10.1016/j.orl.2017.12.005
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 averaged two-replication procedure assesses the quality of a candidate solution to a stochastic program by forming point and confidence interval estimators on its optimality gap. We present an improved averaged two-replication procedure that uses Latin hypercube sampling to form confidence intervals of optimality gap. This new procedure produces tighter and less variable interval widths by reducing the sampling error by root 2. Despite having tighter intervals, it improves an earlier procedure's asymptotic coverage probability bound from (1 - alpha)(2) to (1 - alpha). (C) 2017 Elsevier B.V. All rights reserved.
引用
收藏
页码：173 / 178
页数：6
相关论文
共 40 条
[1]  
[Anonymous], 2007, Pac. J. Optim., DOI DOI 10.18452/2928
[2]  
[Anonymous], 2001, EXERCISES PROBABILIT
[3]  
Banerjee M., ARXIV160504446
[4]   Assessing solution quality in stochastic programs [J].
Bayraksan, Guezin ;
Morton, David P. .
MATHEMATICAL PROGRAMMING, 2006, 108 (2-3) :495-514
[5]   FIXED-WIDTH SEQUENTIAL STOPPING RULES FOR A CLASS OF STOCHASTIC PROGRAMS [J].
Bayraksan, Guezin ;
Pierre-Louis, Peguy .
SIAM JOURNAL ON OPTIMIZATION, 2012, 22 (04) :1518-1548
[6]   A Sequential Sampling Procedure for Stochastic Programming [J].
Bayraksan, Guezin ;
Morton, David P. .
OPERATIONS RESEARCH, 2011, 59 (04) :898-913
[7]  
Biller B., 2006, Handbook in Operations Research and Management Science, V13
[8]  
Chen J., 2014, TECH REP
[9]  
Chiralaksanakul A., STOCHASTIC PROGRAMMI
[10]  
Çinlar E, 2011, GRAD TEXTS MATH, V261, P1, DOI 10.1007/978-0-387-87859-1
1234