arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1712.00709cs.AI
收藏

图着色的模拟退火算法

Simulated Annealing Algorithm for Graph Coloring

Alper Kose, Berke Aral Sonmez, Metin Balaban

摘要:

这个随机漫步项目的目标是编码和实验马尔可夫链蒙特卡罗(MCMC)方法的图着色的问题。在本报告中,我们通过改变\(\mathbf{q}\)(可用于着色的颜色数)和\(\mathbf{c}\)(平均节点度)等参数来绘制成本函数\(\mathbf{H}\)的图。结果是通过使用模拟退火方案,其中温度(\(\mathbfβ\)的倒数)参数在MCMC逐渐降低。

英文摘要:

The goal of this Random Walks project is to code and experiment the Markov Chain Monte Carlo (MCMC) method for the problem of graph coloring. In this report, we present the plots of cost function \(\mathbf{H}\) by varying the parameters like \(\mathbf{q}\) (Number of colors that can be used in coloring) and \(\mathbf{c}\) (Average node degree). The results are obtained by using simulated annealing scheme, where the temperature (inverse of \(\mathbfβ\)) parameter in the MCMC is lowered progressively.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑