Filters








5,439 Hits in 8.0 sec

Stability Selection for Structured Variable Selection [article]

George Philipp, Seunghak Lee, Eric P. Xing
2017 arXiv   pre-print
In this paper, we investigate the applicability of stability selection to structured selection algorithms: the group lasso and the structured input-output lasso.  ...  We give strategies for setting tuning parameters to obtain a good model size under stability selection, and highlight its strengths and weaknesses compared to competing methods screen and clean and cross-validation  ...  Cross-validation executes the sub-algorithm k times.  ... 
arXiv:1712.04688v1 fatcat:nno44yqyxfehhmxxv4bpqt4cge

Resampling procedures to identify important SNPs using a consensus approach

Christopher Pardy, Allan Motyer, Susan Wilson
2011 BMC Proceedings  
A cross-validation LASSO is then used to further select variables. We combine these procedures to guarantee that cross-validation can be used to choose a shrinkage parameter for the LASSO.  ...  We perform our procedure on the first simulated replicate and then validate against the others. Our procedure performs well when predicting Q1 but is less successful for the other outcomes.  ...  If the clinical variables were unavailable, this approach would allow the LASSO model to be fitted. Figure 1 1 LASSO cross-validation plots for affected status.  ... 
doi:10.1186/1753-6561-5-s9-s59 pmid:22373247 pmcid:PMC3287897 fatcat:wthxgteqazaixppiz762nocarq

Model selection procedures for high dimensional genomic data

Allan John Motyer, Sally Galbraith, Susan R Wilson
2011 ANZIAM Journal  
Penalised maximum likelihood estimation is performed with both the lasso and a more recently developed method known as the hyperlasso, with smoothing parameters chosen by cross-validation.  ...  The hyperlasso has a penalty function that favours sparser solutions but with less shrinkage of those variables that are included in the model, when compared to the lasso; however, this comes at extra  ...  Acknowledgements We thank Eric Schadt of Pacific Biosciences for providing the data analysed in this article.  ... 
doi:10.21914/anziamj.v52i0.3970 fatcat:eudjxpiwjnhmpg4hjkbwajoenm

İstatistiksel Öğrenmeye Dayalı Düzenlemeyle Hava Kalitesinin Değerlendirilmesi

Bülent TÜTMEZ
2020 Çukurova Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi  
However, the elastic-net model outperforms the other models both accuracy and robustness (stability).  ...  For the analyses, statistical learning-based regularization procedures such as Ridge, the Lasso and Elastic-net algorithms have been practiced.  ...  Cross Validation-based MSEs In consequence of the simulations, the optimum tuning value has been provided by the smallest cross-validation error.  ... 
doi:10.21605/cukurovaummfd.792412 fatcat:6sxklyu23ndujjasyvp2kje53m

Sparse covariance thresholding for high-dimensional variable selection

X. Jessie Jeng, Z. John Daye
2011 Statistica sinica  
In high dimensions, variable selection methods such as the lasso are often limited by excessive variability and rank deficiency of the sample covariance matrix.  ...  In this paper, we propose the covariance-thresholded lasso, a new class of regression methods that can utilize covariance sparsity to improve variable selection.  ...  Computing resources and support were provided by the Department of Statistics, Purdue University, and the Rosen Center for Advanced Computing (RCAC) of Information Technology at Purdue.  ... 
doi:10.5705/ss.2011.028a fatcat:daglg6xarffwlp46gv34yqmcqm

Sparse covariance thresholding for high-dimensional variable selection [article]

X. Jessie Jeng And Z. John Daye
2010 arXiv   pre-print
In high-dimensions, many variable selection methods, such as the lasso, are often limited by excessive variability and rank deficiency of the sample covariance matrix.  ...  In this paper, we propose the covariance-thresholded lasso, a new class of regression methods that can utilize covariance sparsity to improve variable selection.  ...  Acknowledgment The authors are grateful to Jayanta K. Ghosh and Jian Zhang for helpful comments and discussions.  ... 
arXiv:1006.1146v1 fatcat:75rcwuilijdonawoaku4hqvw6y

Deconfounding and Causal Regularization for Stability and External Validity [article]

Peter Bühlmann, Domagoj Ćevid
2020 arXiv   pre-print
In this sense, we provide additional thoughts to the issue on concept drift, raised by Efron (2020), when the data generating distribution is changing.  ...  We describe how simple and user-friendly techniques improve stability, replicability and distributional robustness in heterogeneous data.  ...  As an alternative to cross-validation, one can use Stability Selection (Meinshausen and Bühlmann, 2010) on the original data.  ... 
arXiv:2008.06234v1 fatcat:ny7axfvicbcczmh24wuaofg2km

Stability SCAD: a powerful approach to detect interactions in large-scale genomic study

Jianwei Gou, Yang Zhao, Yongyue Wei, Chen Wu, Ruyang Zhang, Yongyong Qiu, Ping Zeng, Wen Tan, Dianke Yu, Tangchun Wu, Zhibin Hu, Dongxin Lin (+2 others)
2014 BMC Bioinformatics  
The recently developed stability least absolute shrinkage and selection operator ( S LASSO) has been used to control family-wise error rate, but often at the expense of power (and thus false negative results  ...  with S LASSO analysis.  ...  Acknowledgments The authors thank all of the study participants and research staff for their contributions and commitment to this study.  ... 
doi:10.1186/1471-2105-15-62 pmid:24580776 pmcid:PMC3984751 fatcat:4zxtyqlmqnhxnfk3boimusxnqq

Model selection on tourism forecasting: A comparison between Bayesian model averaging and Lasso
English

Wang Jiyuan, Peng Geng, Wang Shouyang
2017 African Journal of Business Management  
This study compares two popular candidates, which are the Bayesian Model Averaging (BMA) approach and the Least Absolute Shrinkage and Selector Operator (Lasso) approach.  ...  This study tries to tackle the tourism forecasting problem using online search queries.  ...  Commonly, to guarantee the model stability of Lasso such that we can also mitigate model uncertainty to some degree, we apply cross-validation. Basically, we divide the sample into subsamples.  ... 
doi:10.5897/ajbm2016.8249 fatcat:5x7cqcjp4zfbfpcgwmuj47yvia

False discovery control for penalized variable selections with high-dimensional covariates

Kevin He, Xiang Zhou, Hui Jiang, Xiaoquan Wen, Yi Li
2018 Statistical Applications in Genetics and Molecular Biology  
To effectively control the fraction of false discoveries for penalized variable selections, we propose a false discovery controlling procedure.  ...  Modern bio-technologies have produced a vast amount of high-throughput data with the number of predictors much exceeding the sample size.  ...  Acknowledgment: The authors thank Dr. Kirsten Herold at the UM-SPH Writing lab for her helpful suggestions.  ... 
doi:10.1515/sagmb-2018-0038 pmid:30864387 pmcid:PMC6450074 fatcat:ebiwhdfeibgilitv73w3xouiw4

Mouse obesity network reconstruction with a variational Bayes algorithm to employ aggressive false positive control

Benjamin A Logsdon, Gabriel E Hoffman, Jason G Mezey
2012 BMC Bioinformatics  
enter the model without the need for cross-validation or a model selection criterion.  ...  lasso and have bounds on type I error control.  ...  We would also like to thank two anonymous reviewers for suggestions which significantly improved the quality of this manuscript.  ... 
doi:10.1186/1471-2105-13-53 pmid:22471599 pmcid:PMC3338387 fatcat:4ebwp2drtrgczgqovh6qrwjdei

Estimation Stability with Cross Validation (ESCV) [article]

Chinghway Lim, Bin Yu
2015 arXiv   pre-print
Cross-validation (CV) is often used to select the regularization parameter in high dimensional problems.  ...  Our proposed ESCV finds a locally ES-optimal model smaller than the CV choice so that the it fits the data and also enjoys estimation stability property.  ...  ESCV data.zip: Data for the problems described in Section 3.2 and 3.3.  ... 
arXiv:1303.3128v2 fatcat:vz2lhcxojjfv7nbneyj7ow2kmi

Stochastic Stepwise Ensembles for Variable Selection [article]

Lu Xin, Mu Zhu
2011 arXiv   pre-print
In this article, we advocate the ensemble approach for variable selection. We point out that the stochastic mechanism used to generate the variable-selection ensemble (VSE) must be picked with care.  ...  We construct a VSE using a stochastic stepwise algorithm, and compare its performance with numerous state-of-the-art algorithms.  ...  As such, cross validation is out of the question.  ... 
arXiv:1003.5930v2 fatcat:jonuh7qydjaincgvuqhrqw64gm

IPF-LASSO: Integrative L1-Penalized Regression with Penalty Factors for Prediction Based on Multi-Omics Data

Anne-Laure Boulesteix, Riccardo De Bin, Xiaoyu Jiang, Mathias Fuchs
2017 Computational and Mathematical Methods in Medicine  
The penalty factors can be chosen in a fully data-driven fashion by cross-validation or by taking practical considerations into account.  ...  In simulation studies, we compare the prediction performance of our approach, called IPF-LASSO (Integrative LASSO with Penalty Factors) and implemented in the R package ipflasso, with the standard LASSO  ...  Acknowledgments The authors thank Sarah Tegenfeldt for helpful comments. MF was financed by a postdoc grant from Novartis Biomarker to ALB.  ... 
doi:10.1155/2017/7691937 pmid:28546826 pmcid:PMC5435977 fatcat:cswnds3gdvc6fhmsn7g6qy6imm

Predictive and interpretable models via the stacked elastic net

Armin Rauschenberger, Enrico Glaab, Mark van de Wiel, Pier Luigi Martelli
2020 Bioinformatics  
It has a mixing parameter to weight between ridge and lasso regularisation. Instead of selecting one weighting by tuning, we combine multiple weightings by stacking.  ...  Motivation Machine learning in the biomedical sciences should ideally provide predictive and interpretable models.  ...  Median cross-validated logistic deviance against the elastic net mixing parameter, for 'colon' (left), 'leukaemia' (centre), and 'SRBCT' (right).  ... 
doi:10.1093/bioinformatics/btaa535 pmid:32437519 fatcat:gc4cqjofunhllhbzcieoyac4om
« Previous Showing results 1 — 15 out of 5,439 results