arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.02601math.OCcs.LG
收藏

学习困难的最优化问题:数据生成的观点

Learning Hard Optimization Problems: A Data Generation Perspective

Syracuse University(雪城大学);Georgia Institute of Technology(佐治亚理工学院)

James Kotary, Ferdinando Fioretto, Pascal Van Hentenryck

摘要:

最优化问题在我们的社会中无处不在,几乎存在于经济的每一个部分。这些最优化问题中的大多数是NP难的,并且计算量很大,对于大规模的实例,通常需要近似解。机器学习框架学习近似解这些困难的最优化问题是解决这些困难的潜在有前途的途径,特别是当许多密切相关的问题实例必须重复解决时。监督学习框架可以使用预先解决的实例的输出来训练模型。然而,当输出本身是近似值时,当最优化问题具有对称解时,和/或当求解器使用随机化时,紧密相关的实例的解可能表现出大的差异,并且学习任务可能固有地变得更加困难。本文展示了这一关键挑战,将训练数据的波动性与模型近似它的能力联系起来,并提出了一种方法,用于产生更适合监督学习任务的最优化问题的(精确或近似)解决方案。该方法的有效性进行了测试,硬非线性,非凸和离散组合问题。

英文摘要:

Optimization problems are ubiquitous in our societies and are present in almost every segment of the economy. Most of these optimization problems are NP-hard and computationally demanding, often requiring approximate solutions for large-scale instances. Machine learning frameworks that learn to approximate solutions to such hard optimization problems are a potentially promising avenue to address these difficulties, particularly when many closely related problem instances must be solved repeatedly. Supervised learning frameworks can train a model using the outputs of pre-solved instances. However, when the outputs are themselves approximations, when the optimization problem has symmetric solutions, and/or when the solver uses randomization, solutions to closely related instances may exhibit large differences and the learning task can become inherently more difficult. This paper demonstrates this critical challenge, connects the volatility of the training data to the ability of a model to approximate it, and proposes a method for producing (exact or approximate) solutions to optimization problems that are more amenable to supervised learning tasks. The effectiveness of the method is tested on hard non-linear nonconvex and discrete combinatorial problems.

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。

↑