arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.04323cs.ROmath.OC
收藏

学习组合优化问题的结构逼近

Learning structured approximations of combinatorial optimization problems

CERMICS(CERMICS(巴黎路桥学院数学与科学计算中心));Ecole des Ponts(巴黎路桥学院)

Axel Parmentier

摘要:

包括组合优化层的机器学习流水线可以为困难的组合优化问题提供令人惊讶的高效算法。三个问题仍然悬而未决:应该使用哪种体系结构,应该如何学习机器学习模型的参数,以及我们可以从最终算法中获得哪些性能保证?遵循几何深度学习的直觉,我们解释了为什么在设计此类管道时应该使用等变层,并说明了如何在路由,调度和网络设计应用程序上构建此类层。我们介绍了一种学习方法,使学习这样的管道时,训练集只包含困难的优化问题的实例,而不是他们的最佳解决方案,并显示其数值性能在我们的三个应用程序。最后,使用统计学习理论的工具,我们证明了一个定理,显示估计的收敛速度。作为推论,我们得到,如果一个近似算法可以由管道编码的一些参数化,那么学习的管道将保留近似比保证。在我们的网络设计问题上,我们的机器学习管道具有已知最佳近似算法的近似比保证和最佳启发式的数值效率。

英文摘要:

Machine learning pipelines that include a combinatorial optimization layer can give surprisingly efficient heuristics for difficult combinatorial optimization problems. Three questions remain open: which architecture should be used, how should the parameters of the machine learning model be learned, and what performance guarantees can we expect from the resulting algorithms? Following the intuitions of geometric deep learning, we explain why equivariant layers should be used when designing such pipelines, and illustrate how to build such layers on routing, scheduling, and network design applications. We introduce a learning approach that enables to learn such pipelines when the training set contains only instances of the difficult optimization problem and not their optimal solutions, and show its numerical performance on our three applications. Finally, using tools from statistical learning theory, we prove a theorem showing the convergence speed of the estimator. As a corollary, we obtain that, if an approximation algorithm can be encoded by the pipeline for some parametrization, then the learned pipeline will retain the approximation ratio guarantee. On our network design problem, our machine learning pipeline has the approximation ratio guarantee of the best approximation algorithm known and the numerical efficiency of the best heuristic.

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。

↑