Robust instance-optimal recovery of sparse signals at unknown noise levels

DOI10.1093/IMAIAI/IAAB015MaRDI QIDQ5044112zbMATH OpenOpenAlexFDO

Authors Hendrik Bernd Petersen, Peter Jung

Publication date 24 October 2022

Published in Information and Inference: A Journal of the IMA (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2008.08385

zbMATH Keywords

Lassotuningcompressed sensingsparse signalsrecovery techniquestuning-freecompressible signalrLasso

Mathematics Subject Classification ID

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

Abstract: We consider the problem of sparse signal recovery from noisy measurements. Many of frequently used recovery methods rely on some sort of tuning depending on either noise or signal parameters. If no estimates for either of them are available, the noisy recovery problem is significantly harder. The square root LASSO and the least absolute deviation LASSO are known to be noise-blind, in the sense that the tuning parameter can be chosen independent on the noise and the signal. We generalize those recovery methods to the hrlone{} and give a recovery guarantee once the tuning parameter is above a threshold. Moreover, we analyze the effect of a bad chosen tuning parameter mistuning on a theoretic level and prove the optimality of our recovery guarantee. Further, for Gaussian matrices we give a refined analysis of the threshold of the tuning parameter and proof a new relation of the tuning parameter on the dimensions. Indeed, for a certain amount of measurements the tuning parameter becomes independent on the sparsity. Finally, we verify that the least absolute deviation LASSO can be used with random walk matrices of uniformly at random chosen left regular biparitite graphs.

Recommendations

• Sparse signal recovery with exponential-family noise
• Robust sparse recovery via a novel convex model
• Sharp support recovery from noisy random measurements by \(\ell_1\)-minimization
• Sparse recovery with coherent tight frames via analysis Dantzig selector and analysis LASSO
• Perturbation analysis of \(L_{1-2}\) method for robust sparse recovery

Cited in

(11)

• Optimal learning
• Square root LASSO: well-posedness, Lipschitz stability, and the tuning trade-off
• Noise sensitivity of sparse signal representations: reconstruction error bounds for the inverse problem
• Robust group lasso: model and recoverability
• scientific article; zbMATH DE number 6438182 (Why is no real title available?)
• From Sparse Signals to Sparse Residuals for Robust Sensing
• Robust sparse signal reconstructions against basis mismatch and their applications
• Robust recovery of a kind of weighted l1-minimization without noise level
• Analysis non-sparse recovery for relaxed ALASSO
• Consistent parameter estimation for Lasso and approximate message passing
• Consistent parameter estimation for Lasso and approximate message passing

This page was built for publication: Robust instance-optimal recovery of sparse signals at unknown noise levels

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5044112)