arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.00938cs.AIcs.DMcs.LG
收藏

旅行商问题的机器学习构造和局部优化

Machine Learning Constructives and Local Searches for the Travelling Salesman Problem

Università della Svizzera Italiana(瑞士意大利语区大学);Dalle Molle Institute for Artificial Intelligence(达莱莫勒人工智能研究所);University of Modena and Reggio Emilia(摩德纳-雷焦艾米利亚大学)

Tommaso Vitali, Umberto Junior Mele, Luca Maria Gambardella, Roberto Montemanni

摘要:

ML-构造性启发式算法是最近提出的一种方法,也是第一种能够扩展到实际规模的旅行商问题的混合方法。它结合了机器学习技术和经典的优化技术。在本文中,我们对原始深度学习模型的计算权重进行了改进。此外,由于更简单的模型减少了执行时间,因此探索了添加本地搜索阶段的可能性,以进一步提高性能。实验结果证实了所提出的改进的质量。

英文摘要:

The ML-Constructive heuristic is a recently presented method and the first hybrid method capable of scaling up to real scale traveling salesman problems. It combines machine learning techniques and classic optimization techniques. In this paper we present improvements to the computational weight of the original deep learning model. In addition, as simpler models reduce the execution time, the possibility of adding a local-search phase is explored to further improve performance. Experimental results corroborate the quality of the proposed improvements.

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。

↑