PROBABILISTIC BOUNDS (VIA LARGE DEVIATIONS) FOR THE SOLUTIONS OF STOCHASTIC-PROGRAMMING PROBLEMS

被引：43

作者：

KANIOVSKI, YM

KING, AJ

WETS, RJB

机构：

[1] INT INST APPL SYST ANAL,LAXENBURG,AUSTRIA

[2] IBM CORP,THOMAS J WATSON RES CTR,DEPT MATH SCI,YORKTOWN HTS,NY 10598

[3] UNIV CALIF DAVIS,DEPT MATH,DAVIS,CA 95616

来源：

ANNALS OF OPERATIONS RESEARCH | 1995年 / 56卷

关键词：

EPI-DISTANCE; LARGE DEVIATIONS; STOCHASTIC PROGRAMS; CONVERGENCE;

D O I：

10.1007/BF02031707

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：

Several exponential bounds are derived by means of the theory of large deviations for the convergence of approximate solutions of stochastic optimization problems. The basic results show that the solutions obtained by replacing the original distribution by an empirical distribution provides an effective tool for solving stochastic programming problems.

引用

页码：189 / 208

页数：20

共 29 条

[1]

[Anonymous], 1989, LARGE DEVIATIONS

[2] QUANTITATIVE STABILITY OF VARIATIONAL SYSTEMS .1. THE EPIGRAPHICAL DISTANCE [J].