Online Hyperparameter-Free Sparse Estimation Method

DOI10.1109/TSP.2015.2421472MaRDI QIDQ4580648zbMATH OpenOpenAlexFDO

Authors Dave Zachariah, Petre Stoica

Publication date 22 August 2018

Published in IEEE Transactions on Signal Processing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1505.01461

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Abstract: In this paper we derive an online estimator for sparse parameter vectors which, unlike the LASSO approach, does not require the tuning of any hyperparameters. The algorithm is based on a covariance matching approach and is equivalent to a weighted version of the square-root LASSO. The computational complexity of the estimator is of the same order as that of the online versions of regularized least-squares (RLS) and LASSO. We provide a numerical comparison with feasible and infeasible implementations of the LASSO and RLS to illustrate the advantage of the proposed online hyperparameter-free estimator.

Recommendations

• Online sparse identification for regression models
• Online Sparse Gaussian Process Regression and Its Applications
• Sparse Online Variational Bayesian Regression
• Sparse on-line Gaussian processes
• Sparse online principal component analysis for parameter estimation in factor model
• scientific article; zbMATH DE number 6860836
• Variable Screening for Sparse Online Regression
• scientific article; zbMATH DE number 5308323
• Online learning for matrix factorization and sparse coding
• scientific article; zbMATH DE number 5633833

Cited in

(4)

• Sparse Online Variational Bayesian Regression
• scientific article; zbMATH DE number 6860836 (Why is no real title available?)
• Recursive nonlinear-system identification using latent variables
• Online Adaptive Estimation of Sparse Signals: Where RLS Meets the $\ell_1$-Norm

This page was built for publication: Online Hyperparameter-Free Sparse Estimation Method

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4580648)