ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1304.0682
41
58

Sparse Signal Processing with Linear and Nonlinear Observations: A Unified Shannon-Theoretic Approach

2 April 2013
Cem Aksoylar
George Atia
Venkatesh Saligrama
ArXivPDFHTML
Abstract

We derive fundamental sample complexity bounds for recovering sparse and structured signals for linear and nonlinear observation models including sparse regression, group testing, multivariate regression and problems with missing features. In general, sparse signal processing problems can be characterized in terms of the following Markovian property. We are given a set of NNN variables X1,X2,…,XNX_1,X_2,\ldots,X_NX1​,X2​,…,XN​, and there is an unknown subset of variables S⊂{1,…,N}S \subset \{1,\ldots,N\}S⊂{1,…,N} that are relevant for predicting outcomes YYY. More specifically, when YYY is conditioned on {Xn}n∈S\{X_n\}_{n\in S}{Xn​}n∈S​ it is conditionally independent of the other variables, {Xn}n∉S\{X_n\}_{n \not \in S}{Xn​}n∈S​. Our goal is to identify the set SSS from samples of the variables XXX and the associated outcomes YYY. We characterize this problem as a version of the noisy channel coding problem. Using asymptotic information theoretic analyses, we establish mutual information formulas that provide sufficient and necessary conditions on the number of samples required to successfully recover the salient variables. These mutual information expressions unify conditions for both linear and nonlinear observations. We then compute sample complexity bounds for the aforementioned models, based on the mutual information expressions in order to demonstrate the applicability and flexibility of our results in general sparse signal processing models.

View on arXiv
Comments on this paper