arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.06114stat.MEmath.STstat.TH
收藏

具有最优性保证的同步特征选择与异常值检测

Simultaneous Feature Selection and Outlier Detection with Optimality Guarantees

Scuola Normale Superiore(高等师范学院);Penn State University(宾夕法尼亚州立大学);Sant’Anna School of Advanced Studies(圣安娜高等研究学院);Istituto di Analisi dei Sistemi ed Informatica, Consiglio Nazionale delle Ricerche(意大利国家研究委员会系统与信息分析研究所)

Luca Insolia, Ana Kenney, Francesca Chiaromonte, Giovanni Felici

AI总结:

针对响应与设计矩阵同时受均值漂移异常值污染的高维回归,提出基于混合整数规划的同步特征选择与异常值检测框架,并给出最优性、oracle 性质及崩溃点理论保证。

摘要:

在过去十年中,能够容忍异常值的稀疏估计方法得到了广泛研究。我们针对受多个均值漂移异常值污染的高维回归问题为该研究作出贡献,这些异常值同时影响响应变量和设计矩阵。我们为此类问题开发了一个通用框架,并提出使用混合整数规划来同步执行特征选择和异常值检测,且具备可证明的最优保证。我们刻画了该方法的理论性质,即稳健强 oracle 性质的充分必要条件(该性质允许特征数量随样本量呈指数增长)、参数的最优估计,以及所得估计量的崩溃点。此外,我们提供了计算高效的过程来调节整数约束并对算法进行热启动。通过数值模拟,以及一项研究人类微生物组与儿童肥胖之间关系的应用,我们表明所提方法相比现有启发式方法具有更优越的性能。

英文摘要:

Sparse estimation methods capable of tolerating outliers have been broadly investigated in the last decade. We contribute to this research considering high-dimensional regression problems contaminated by multiple mean-shift outliers which affect both the response and the design matrix. We develop a general framework for this class of problems and propose the use of mixed-integer programming to simultaneously perform feature selection and outlier detection with provably optimal guarantees. We characterize the theoretical properties of our approach, i.e. a necessary and sufficient condition for the robustly strong oracle property, which allows the number of features to exponentially increase with the sample size; the optimal estimation of the parameters; and the breakdown point of the resulting estimates. Moreover, we provide computationally efficient procedures to tune integer constraints and to warm-start the algorithm. We show the superior performance of our proposal compared to existing heuristic methods through numerical simulations and an application investigating the relationships between the human microbiome and childhood obesity.

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。

↑