Penalized Interaction Estimation for Ultrahigh Dimensional Quadratic Regression

Penalized Interaction Estimation for Ultrahigh Dimensional Quadratic Regression
复制标题

超高维二次回归的惩罚交互估计

DOI:
10.5705/ss.202019.0081
复制
发表时间:
2019-01
期刊:
影响因子:
1.4
通讯作者:
Liping Zhu
Liping Zhu
中科院分区:
数学3区
文献类型:
--
作者:
Cheng Wang;Binyan Jiang;Liping Zhu

文献摘要

参考文献

相似文献

二次回归超越了线性模型,同时包含了主效应和协变量之间的交互作用。在过去的十年里,高维二次回归中的交互作用估计问题受到了广泛的关注。在这篇文章中,我们介绍了一种新的方法,它允许我们分别估计主效应和相互作用。与现有的超高维二次回归方法不同,我们的建议不需要广泛使用的遗传假设。此外,我们提出的估计有明确的公式,并且在总体水平上遵守不变性原理。我们估计了惩罚凸损失函数下矩阵形式的相互作用。结果表明,即使协变量维度是样本大小的指数级,估计也是一致的。我们开发了一种高效的ADMM算法来实现惩罚估计。该ADMM算法充分挖掘了矩阵乘法运算代价低廉的特点,比现有的惩罚算法如所有对套索算法具有更高的效率。我们通过广泛的数值研究展示了我们的建议的良好性能。
Quadratic regression goes beyond the linear model by simultaneously including main effects and interactions between the covariates. The problem of interaction estimation in high dimensional quadratic regression has received extensive attention in the past decade. In this article we introduce a novel method which allows us to estimate the main effects and interactions separately. Unlike existing methods for ultrahigh dimensional quadratic regressions, our proposal does not require the widely used heredity assumption. In addition, our proposed estimates have explicit formulas and obey the invariance principle at the population level. We estimate the interactions of matrix form under penalized convex loss function. The resulting estimates are shown to be consistent even when the covariate dimension is an exponential order of the sample size. We develop an efficient ADMM algorithm to implement the penalized estimation. This ADMM algorithm fully explores the cheap computational cost of matrix multiplication and is much more efficient than existing penalized methods such as all pairs LASSO. We demonstrate the promising performance of our proposal through extensive numerical studies.
DOI: 10.1038/nrg2579
发表时间: 2009-06
期刊: Nature reviews. Genetics
影响因子: --
作者:
Cordell HJ
通讯作者: Cordell HJ
DOI: 10.1214/14-aos1233
发表时间: 2014-10-01
影响因子: 4.5
作者:
Jiang, Bo;Liu, Jun S.
通讯作者: Liu, Jun S.
DOI: 10.1007/s10107-016-1034-2
发表时间: 2017-03-01
影响因子: 2.7
作者:
Hong, Mingyi;Luo, Zhi-Quan
通讯作者: Luo, Zhi-Quan
DOI: 10.1086/321276
发表时间: 2001-07-01
影响因子: 9.8
作者:
Ritchie, MD;Hahn, LW;Moore, JH
通讯作者: Moore, JH
DOI: 10.1080/10618600.2015.1067217
发表时间: 2016
期刊: Journal of computational and graphical statistics : a joint publication of American Statistical Association, Institute of Mathematical Statistics, Interface Foundation of North America
影响因子: --
作者:
Haris A;Witten D;Simon N
通讯作者: Simon N