arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.01485cs.LGstat.ML
收藏

包围盒特征选择器稳定性的快速估计方法

Fast Estimation Method for the Stability of Ensemble Feature Selectors

The University of Tokyo(东京大学);Preferred Networks, Inc.(Preferred Networks 公司)

Rina Onda, Zhengyan Gao, Masaaki Kotera, Kenta Oono

摘要:

优选地,特征选择器是\textit{stable},以获得更好的可解释性和稳健的预测。集成被认为是有效的,以提高稳定性的特征选择器。由于集成是耗时的,它是可取的,以减少计算成本来估计集成特征选择器的稳定性。我们提出了一个特征选择器的模拟器,并将其应用于集成特征选择器的稳定性的快速估计。据我们所知,这是第一个研究,估计集成功能选择器的稳定性,并减少了计算时间的理论和经验。

英文摘要:

It is preferred that feature selectors be \textit{stable} for better interpretabity and robust prediction. Ensembling is known to be effective for improving the stability of feature selectors. Since ensembling is time-consuming, it is desirable to reduce the computational cost to estimate the stability of the ensemble feature selectors. We propose a simulator of a feature selector, and apply it to a fast estimation of the stability of ensemble feature selectors. To the best of our knowledge, this is the first study that estimates the stability of ensemble feature selectors and reduces the computation time theoretically and empirically.

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。

↑