arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2401.09436math.OC
收藏

Oracle模型中非凸函数全局最优值的不可计算性

Uncomputability of Global Optima for Nonconvex Functions in the Oracle Model

K Lakshmanan

AI总结:

研究Oracle模型中非凸函数全局最优值的不可计算性,证明仅能访问函数Oracle的算法无法计算全局最小值,并刻画全局最优值可计算的充要条件,提出基于吸引域的收敛算法。

摘要:

虽然众所周知,寻找非凸函数的近似最优值在计算上是难解的,但我们表明,在Oracle模型中,该问题实际上是不可计算的。具体而言,我们证明,仅能访问函数Oracle的算法无法计算全局最小值,甚至无法计算最小化器或最小值的ε-近似。随后,我们刻画了全局最优值变得可计算的一个必要且充分条件,该条件基于存在一个包含全局最优性条件的可计算谓词。作为说明性示例,我们将全局最小化器周围的吸引域视为这样一个性质,并提出一种简单算法,当已知吸引域的界限时,该算法收敛到全局最小值。最后,我们在标准基准函数上提供数值实验,以展示该算法的实际性能。

英文摘要:

While it is well known that finding approximate optima of non-convex functions is computationally intractable, we show that the problem is, in fact, uncomputable in the oracle model. Specifically, we prove that no algorithm with access only to a function oracle can compute the global minimum or even an $ε$-approximation of the minimizer or minimal value. We then characterize a necessary and sufficient condition under which global optima become computable, based on the existence of a computable predicate that subsumes the global optimality condition. As an illustrative example, we consider the basin of attraction around a global minimizer as such a property and propose a simple algorithm that converges to the global minimum when a bound on the basin is known. Finally, we provide numerical experiments on standard benchmark functions to demonstrate the algorithm's practical performance.

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。

↑