基于模拟退火准则的谱投影梯度算法

Spectral Projection Gradient Algorithm Based on Simulated Annealing Criterion

针对简单凸集约束优化问题,提出了一种基于模拟退火准则的谱投影梯度方法.在适当的假设下,证明了算法的全局收敛性.数值实验结果表明,与已有的算法比较,本文所提出的算法在求解该类问题时更有效、更具竞争力.

In this paper, a spectral projection gradient algorithm was proposed based on simulated annealing criterion for solving a convex constrained optimization problem. The algorithm is a combination of spectral projection gradient algorithm and simulated annealing criterion. Under suitable assumptions, global convergence of the proposed algorithm was proved. Numerical experiments showed that the proposed algorithm is more effective and competitive than the existing algorithms in solving the problems.