On Minimization of a Quadratic Binary Functional

Abstract

The problem of minimization of a quadratic functional depending on great number of binary variables is examined. 3 variants of minimization procedure are studied with the aid of computer simulation for spin-glass matrices. It is shown that under other equal conditions evident superiority has the maximal dynamics (the greedy algorithm). The dependence of the results on a distance between start points and the ground state is investigated. It is determined that the character of distribution of local minima depends on this distance crucially.