Improving Lasso for model selection and prediction

DOI10.1111/SJOS.12546MaRDI QIDQ5043783zbMATH OpenOpenAlexFDO

Authors Piotr Pokarowski, Wojciech Rejchel, Agnieszka Sołtys, Michał Frej, Jan Mielniczuk

Publication date 6 October 2022

Published in Scandinavian Journal of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1907.03025

zbMATH Keywords

convex loss functionempirical processgeneralized information criterionhigh-dimensional regressionpenalized estimationselection consistency

Mathematics Subject Classification ID

Ridge regression; shrinkage estimators (Lasso) (62J07)

Abstract: It is known that the Thresholded Lasso (TL), SCAD or MCP correct intrinsic estimation bias of the Lasso. In this paper we propose an alternative method of improving the Lasso for predictive models with general convex loss functions which encompass normal linear models, logistic regression, quantile regression or support vector machines. For a given penalty we order the absolute values of the Lasso non-zero coefficients and then select the final model from a small nested family by the Generalized Information Criterion. We derive exponential upper bounds on the selection error of the method. These results confirm that, at least for normal linear models, our algorithm seems to be the benchmark for the theory of model selection as it is constructive, computationally efficient and leads to consistent model selection under weak assumptions. Constructivity of the algorithm means that, in contrast to the TL, SCAD or MCP, consistent selection does not rely on the unknown parameters as the cone invertibility factor. Instead, our algorithm only needs the sample size, the number of predictors and an upper bound on the noise parameter. We show in numerical experiments on synthetic and real-world data sets that an implementation of our algorithm is more accurate than implementations of studied concave regularizations. Our procedure is contained in the R package "DMRnet" and available on the CRAN repository.

Recommendations

• The predictive Lasso
• Lasso with convex loss: model selection consistency and estimation
• A note on the Lasso and related procedures in model selection
• Least angle regression. (With discussion)
• The adaptive and the thresholded Lasso for potentially misspecified models (and a lower bound for the Lasso)

Cited in

(12)

• Improving the prediction performance of the Lasso by subtracting the additive structural noises
• On Lasso refitting strategies
• Improved loss estimation for the lasso: a variable selection tool
• Lasso–type and Heuristic Strategies in Model Selection and Forecasting
• scientific article; zbMATH DE number 5957408 (Why is no real title available?)
• DMRnet
• Tuning Parameter Selection in the LASSO with Unspecified Propensity
• Improvement on LASSO-type estimator in nonparametric regression
• Strong Rules for Discarding Predictors in Lasso-Type Problems
• Structure learning for continuous time Bayesian networks via penalized likelihood
• Variable selection via thresholding
• A unified framework for pattern recovery in penalized and thresholded estimation and its geometry

Describes a project that uses

Uses Software

• sparsenet
• R

This page was built for publication: Improving Lasso for model selection and prediction

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5043783)