关键词: 半定规划, 信赖域算法, 非单调策略, 内点算法, 无约束优化

Abstract: In order to improve the operational efficiency of SemiDefinite Programming (SDP), a new nonmonotonic trust region algorithm was proposed. The SDP problem and its duality problem were transformed into unconstrained optimization problem and the trust region subproblem was constructed, the trust region radius correction condition was modified. When the initial search point was near the canyon, the global optimal solution still could be found. The experimental results show that the number of iterations of the algorithm is less than the classical interior point algorithm for small and medium scale semidefinite programming problems, and the proposed algorithm works faster.

Key words: SemiDefinite Programming (SDP), trust region algorithm, nonmonotonic strategy, interior algorithm, unconstrained optimization