High-Dimensional Estimation of Structured Signals From Non-Linear Observations With General Convex Loss Functions

DOI10.1109/TIT.2016.2642993MaRDI QIDQ5280856zbMATH OpenFDO

Authors Martin Genzel

Publication date 27 July 2017

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1602.03436

Mathematics Subject Classification ID

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

Abstract: In this paper, we study the issue of estimating a structured signal $x_{0}inmathbb{R}^n$ from non-linear and noisy Gaussian observations. Supposing that $x_0$ is contained in a certain convex subset $Ksubsetmathbb{R}^n$, we prove that accurate recovery is already feasible if the number of observations exceeds the effective dimension of $K$, which is a common measure for the complexity of signal classes. It will turn out that the possibly unknown non-linearity of our model affects the error rate only by a multiplicative constant. This achievement is based on recent works by Plan and Vershynin, who have suggested to treat the non-linearity rather as noise which perturbs a linear measurement process. Using the concept of restricted strong convexity, we show that their results for the generalized Lasso can be extended to a fairly large class of convex loss functions. Moreover, we shall allow for the presence of adversarial noise so that even deterministic model inaccuracies can be coped with. These generalizations particularly give further evidence of why many standard estimators perform surprisingly well in practice, although they do not rely on any knowledge of the underlying output rule. To this end, our results provide a unified and general framework for signal reconstruction in high dimensions, covering various challenges from the fields of compressed sensing, signal processing, and statistical learning.

Cited in

(9)

• Applied harmonic analysis and data processing. Abstracts from the workshop held March 25--31, 2018
• Optimal combination of linear and spectral estimators for generalized linear models
• Misspecified nonconvex statistical optimization for sparse phase retrieval
• \(\ell^1\)-analysis minimization and generalized (co-)sparsity: when does recovery succeed?
• Generic error bounds for the generalized Lasso with sub-exponential data
• Ising model selection using ℓ ₁-regularized linear regression: a statistical mechanics analysis*
• scientific article; zbMATH DE number 7306923 (Why is no real title available?)
• A unified approach to uniform signal recovery from nonlinear observations
• Uniform recovery guarantees for quantized corrupted sensing using structured or generative priors

This page was built for publication: High-Dimensional Estimation of Structured Signals From Non-Linear Observations With General Convex Loss Functions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5280856)