MEAN FIELD ANNEALING - A FORMALISM FOR CONSTRUCTING GNC-LIKE ALGORITHMS

被引：46

作者：

BILBRO, GL ^{[1
]}

SNYDER, WE ^{[1
]}

GARNIER, SJ ^{[1
]}

GAULT, JW ^{[1
]}

机构：

[1] WAKE FOREST UNIV,BOWMAN GRAY SCH MED,DEPT RADIOL,WINSTON SALEM,NC 27103

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 1992年 / 3卷 / 01期

关键词：

SIMULATED ANNEALING; MEAN FIELD APPROXIMATION; GRADUATED NONCONVEXITY;

D O I：

10.1109/72.105426

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We approach optimization problems using mean field annealing (MFA), which is a deterministic approximation, using mean field theory and based on Peierls's inequality, to simulated annealing. The MFA mathematics are applied to three different objective function examples. In each case, MFA produces a minimization algorithm that is a type of graduated nonconvexity. When applied to the "weak membrane" objective, MFA results in an algorithm qualitatively identical to the published GNC algorithm. One of the examples, MFA applied to a piecewise-constant objective function, is then compared experimentally with the corresponding GNC weak-membrane algorithm. The mathematics of MFA are shown to provide a powerful and general tool for deriving optimization algorithms.

引用

页码：131 / 138

页数：8