arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.06148math.OCcs.AIcs.ITmath.IT
收藏

优化器的可计算性

Computability of Optimizers

Ludwig-Maximilians University of Munich(慕尼黑大学);Technical University of Munich(慕尼黑工业大学);Ruhr University Bochum(波鸿鲁尔大学);University of Tromsø(特罗姆瑟大学)

Yunseok Lee, Holger Boche, Gitta Kutyniok

摘要:

最优化问题是当今科学和技术领域的主要问题。然而,目前,这些问题的求解器几乎完全在数字硬件上运行。使用图灵机作为任何类型的数字硬件的数学模型,在本文中,我们分析了解决最优化问题的概念方法的基本局限性。由于在大多数应用程序中,优化器本身比相应函数的最优值更重要,因此我们将关注优化器的可计算性。事实上,我们将证明,在各种情况下,优化器在图灵机上是无法实现的,因此在数字计算机上也是如此。此外,更糟糕的是,不存在一个图灵机,它近似优化器本身达到一定的恒定误差。我们证明了这样的结果的各种著名的问题,从非常不同的领域,包括人工智能,金融数学,和信息论,往往得出更强的结果,这些问题是不是巴拿赫-马祖尔可计算的,也不是甚至在近似意义上。

英文摘要:

Optimization problems are a staple of today's scientific and technical landscape. However, at present, solvers of such problems are almost exclusively run on digital hardware. Using Turing machines as a mathematical model for any type of digital hardware, in this paper, we analyze fundamental limitations of this conceptual approach of solving optimization problems. Since in most applications, the optimizer itself is of significantly more interest than the optimal value of the corresponding function, we will focus on computability of the optimizer. In fact, we will show that in various situations the optimizer is unattainable on Turing machines and consequently on digital computers. Moreover, even worse, there does not exist a Turing machine, which approximates the optimizer itself up to a certain constant error. We prove such results for a variety of well-known problems from very different areas, including artificial intelligence, financial mathematics, and information theory, often deriving the even stronger result that such problems are not Banach-Mazur computable, also not even in an approximate sense.

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。

↑