Variable selection via RIVAL (removing irrelevant variables amidst Lasso iterations) and its application to nuclear material detection

Authors:
Paul Kump;Er-Wei Bai;Kung-Sik Chan;Bill Eichinger;Kang Li
Affiliations:
Department of Electrical and Computer Engineering, University of Iowa, Iowa City, IA 52242, United States;Department of Electrical and Computer Engineering, University of Iowa, Iowa City, IA 52242, United States and School of Electronics, Electrical Engineering and Computer Science, Queen's University ...;Department of Statistics, University of Iowa, Iowa City, IA 52242, United States;Department of Civil Engineering, University of Iowa, Iowa City, IA 52242, United States;School of Electronics, Electrical Engineering and Computer Science, Queen's University, Belfast BT7 1NN, UK
Venue:
Automatica (Journal of IFAC)
Year:
2012

Citing 6
Cited 0

Better subset regression using the nonnegative garrote

Technometrics
On Model Selection Consistency of Lasso

The Journal of Machine Learning Research
Model-based deconvolution of genome-wide DNA binding

Bioinformatics
Fast orthogonal least squares algorithm for efficient subset modelselection

IEEE Transactions on Signal Processing
A two-stage algorithm for identification of nonlinear dynamic systems

Automatica (Journal of IFAC)
Regressor selection with the analysis of variance method

Automatica (Journal of IFAC)

Quantified Score

Hi-index	22.14

Visualization

Abstract

In many situations, the number of data points is fixed, and the asymptotic convergence results of popular model selection tools may not be useful. A new algorithm for model selection, RIVAL (removing irrelevant variables amidst Lasso iterations), is presented and shown to be particularly effective for a large but fixed number of data points. The algorithm is motivated by an application of nuclear material detection where all unknown parameters are to be non-negative. Thus, positive Lasso and its variants are analyzed. Then, RIVAL is proposed and is shown to have some desirable properties, namely the number of data points needed to have convergence is smaller than existing methods.