期刊
JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION
卷 85, 期 1, 页码 62-76出版社
TAYLOR & FRANCIS LTD
DOI: 10.1080/00949655.2014.929131
关键词
model selection; feature selection; algorithm configuration; survival analysis; machine learning; high-dimensional data; racing; parameter tuning
资金
- Deutsche Forschungsgemeinschaft (DFG) within the Collaborative Research Center [SFB 876, SFB 823]
Many different models for the analysis of high-dimensional survival data have been developed over the past years. While some of the models and implementations come with an internal parameter tuning automatism, others require the user to accurately adjust defaults, which often feels like a guessing game. Exhaustively trying out all model and parameter combinations will quickly become tedious or infeasible in computationally intensive settings, even if parallelization is employed. Therefore, we propose to use modern algorithm configuration techniques, e.g. iterated F-racing, to efficiently move through the model hypothesis space and to simultaneously configure algorithm classes and their respective hyperparameters. In our application we study four lung cancer microarray data sets. For these we configure a predictor based on five survival analysis algorithms in combination with eight feature selection filters. We parallelize the optimization and all comparison experiments with the BatchJobs and BatchExperiments R packages.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据