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 2109.06584cs.NEcs.AI
收藏

借助复杂性理论的提示选择合适的算法

Choosing the Right Algorithm With Hints From Complexity Theory

École Polytechnique, CNRS(法国国家科学研究中心巴黎综合理工学院);Institut Polytechnique de Paris(巴黎理工学院);Southern University of Science and Technology(南方科技大学)

Shouda Wang, Weijie Zheng, Benjamin Doerr

AI总结:

本文利用黑盒复杂性理论为 DLB 基准选择算法,证明 Metropolis 可达二次最优时间,并由人工算法启发得到 $O(n\log n)$ 的 sig-cGA。

摘要:

面对一个新颖的优化问题时,要从众多不同的搜索启发式方法中选择一种合适的算法是很困难的。在这项工作中,我们认为,某一广泛黑盒优化器类别中何种算法可能是最佳算法这一纯学术问题,能够为应朝哪个方向寻找优秀的成熟优化启发式方法提供富有成效的指示。我们在最近提出的 DLB 基准上展示了这种方法;对于该基准,唯一已知的结果是若干经典进化算法具有 $O(n^3)$ 运行时间,以及一种分布估计算法具有 $O(n^2 \log n)$ 运行时间。我们发现一元无偏黑盒复杂性仅为 $O(n^2)$,这表明 Metropolis 算法是一个值得关注的候选方法,并且我们证明它能在二次时间内解决 DLB 问题。由于我们同时证明在一元无偏算法类别中无法获得更好的运行时间,我们将注意力转向使用更多父代信息来生成新解的算法。一种具有 $O(n \log n)$ 运行时间的此类人工算法引出如下结果:基于显著性的紧凑遗传算法(sig-cGA)也能够以高概率在 $O(n \log n)$ 时间内解决 DLB 问题。我们的实验显示,Metropolis 算法具有异常出色的性能;对于合理规模的问题,它显然是所有被考察算法中最好的。

英文摘要:

Choosing a suitable algorithm from the myriads of different search heuristics is difficult when faced with a novel optimization problem. In this work, we argue that the purely academic question of what could be the best possible algorithm in a certain broad class of black-box optimizers can give fruitful indications in which direction to search for good established optimization heuristics. We demonstrate this approach on the recently proposed DLB benchmark, for which the only known results are $O(n^3)$ runtimes for several classic evolutionary algorithms and an $O(n^2 \log n)$ runtime for an estimation-of-distribution algorithm. Our finding that the unary unbiased black-box complexity is only $O(n^2)$ suggests the Metropolis algorithm as an interesting candidate and we prove that it solves the DLB problem in quadratic time. Since we also prove that better runtimes cannot be obtained in the class of unary unbiased algorithms, we shift our attention to algorithms that use the information of more parents to generate new solutions. An artificial algorithm of this type having an $O(n \log n)$ runtime leads to the result that the significance-based compact genetic algorithm (sig-cGA) can solve the DLB problem also in time $O(n \log n)$ with high probability. Our experiments show a remarkably good performance of the Metropolis algorithm, clearly the best of all algorithms regarded for reasonable problem sizes.

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。

↑