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 2209.06642math.OCcs.LGstat.ME
收藏

一个面向Optimization的鲁棒科学机器学习:一个新的鲁棒性定理

A Robust Scientific Machine Learning for Optimization: A Novel Robustness Theorem

University of Porto(波尔图大学);Universidade Federal da Bahia(巴伊亚联邦大学)

Luana P. Queiroz, Carine M. Rebello, Erber A. Costa, Vinicius V. Santana, Alirio E. Rodrigues, Ana M. Ribeiro, Idelfonso B. R. Nogueira

摘要:

科学机器学习(SciML)是一个在几个不同应用领域越来越受关注的领域。在优化上下文中,基于SciML的工具使得能够开发更有效的最优化方法。然而,实施SciML工具进行优化必须严格评估和谨慎执行。这项工作提出了一个鲁棒性测试,保证多目标SciML为基础的优化的鲁棒性,通过显示其结果尊重通用逼近定理的推导。该测试是适用于一种新的方法,这是在一系列的基准说明其一致性进行评估的框架。此外,所提出的方法的结果进行了比较与可行域的严格优化,这需要一个显着更高的计算工作量。因此,这项工作提供了一种鲁棒性测试,以保证在多目标优化中应用SciML工具时的鲁棒性,并且计算量比现有替代方案更低。

英文摘要:

Scientific machine learning (SciML) is a field of increasing interest in several different application fields. In an optimization context, SciML-based tools have enabled the development of more efficient optimization methods. However, implementing SciML tools for optimization must be rigorously evaluated and performed with caution. This work proposes the deductions of a robustness test that guarantees the robustness of multiobjective SciML-based optimization by showing that its results respect the universal approximator theorem. The test is applied in the framework of a novel methodology which is evaluated in a series of benchmarks illustrating its consistency. Moreover, the proposed methodology results are compared with feasible regions of rigorous optimization, which requires a significantly higher computational effort. Hence, this work provides a robustness test for guaranteed robustness in applying SciML tools in multiobjective optimization with lower computational effort than the existent alternative.

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。

↑