Probing for Sparse and Fast Variable Selection with Model-Based Boosting.

Probing for Sparse and Fast Variable Selection with Model-Based Boosting.
复制标题

DOI:
10.1155/2017/1421409
复制
发表时间:
2017
影响因子:
--
通讯作者:
Bischl B
Bischl B
中科院分区:
工程技术4区
文献类型:
--
作者:
Thomas J;Hepp T;Mayr A;Bischl B

文献摘要

参考文献

被引文献

相似文献

提出了一种基于模型梯度提升和随机变量置换的变量选择方法。基于模型的提升是一种在执行变量选择的同时拟合统计模型的工具。拟合的缺点在于需要对稍微改变的数据进行多个模型拟合(例如,交叉验证或自举)以找到提升迭代的最佳次数并防止过拟合。在我们提出的方法中,我们用真实变量的随机排列版本(所谓的阴影变量)来增加数据集,并在将这样的变量添加到模型中时立即停止逐步拟合。这允许在模型的单次拟合中选择变量,而无需进一步的参数调整。我们表明,我们的探测方法可以与最先进的选择方法,如稳定性选择在高维分类基准,并将其应用于三个基因表达数据集。
We present a new variable selection method based on model-based gradient boosting and randomly permuted variables. Model-based boosting is a tool to fit a statistical model while performing variable selection at the same time. A drawback of the fitting lies in the need of multiple model fits on slightly altered data (e.g., cross-validation or bootstrap) to find the optimal number of boosting iterations and prevent overfitting. In our proposed approach, we augment the data set with randomly permuted versions of the true variables, so-called shadow variables, and stop the stepwise fitting as soon as such a variable would be added to the model. This allows variable selection in a single fit of the model without requiring further parameter tuning. We show that our probing approach can compete with state-of-the-art selection methods like stability selection in a high-dimensional classification benchmark and apply it on three gene expression data sets.
DOI: 10.1016/j.neuroimage.2011.11.054
发表时间: 2012-02-15
期刊: NEUROIMAGE
影响因子: 5.7
作者:
Ryali, Srikanth;Chen, Tianwen;Supekar, Kaustubh;Menon, Vinod
通讯作者: Menon, Vinod
DOI: 10.1186/s12859-016-1149-8
发表时间: 2016-07-22
期刊: BMC bioinformatics
影响因子: 3
作者:
Mayr A;Hofner B;Schmid M
通讯作者: Schmid M
DOI: 10.1186/s12859-015-0575-3
发表时间: 2015-05-06
期刊: BMC bioinformatics
影响因子: 3
作者:
Hofner B;Boccuto L;Göker M
通讯作者: Göker M
DOI: 10.1038/nbt.1658
发表时间: 2010-07-01
影响因子: 46.9
作者:
Mallick, Parag;Kuster, Bernhard
通讯作者: Kuster, Bernhard
DOI: 10.1038/srep10312
发表时间: 2015-05-19
期刊: Scientific reports
影响因子: 4.6
作者:
Bermingham ML;Pong-Wong R;Spiliopoulou A;Hayward C;Rudan I;Campbell H;Wright AF;Wilson JF;Agakov F;Navarro P;Haley CS
通讯作者: Haley CS