透過您的圖書館登入
IP:18.217.182.45
  • 期刊
  • OpenAccess

Statistical Computation Algorithm Based on Markov Chain Monte Carlo Sampling to Solve Multivariable Nonlinear Optimization

並列摘要


This paper proposes a method to solve multivariable nonlinear optimization problem based on MCMC statistical sampling. Theoretical analysis proves that the maximum statistic converges to the maximum point of probability density. From this convergence property, we establish a newly algorithm to find the best solution of an optimization through largely MCMC sampling in condition that the exact generalized probability density function has been designed. The MCMC optimization algorithm needs less iterate variables reserved so that the computing speed is relatively high. Finally, we build a Markov chain model to demonstrate the dynamic movement of ladderlike labour transfer with multiparamter, and we practice this MCMC sampling optimization algorithm to find parameters estimations. The optimization results are reasonable and from which we obtain the short-term and long-term forecast of labour movements.

延伸閱讀