English

Simple Bounds for Noisy Linear Inverse Problems with Exact Side Information

Information Theory 2013-12-06 v2 math.IT Optimization and Control Statistics Theory Statistics Theory

Abstract

This paper considers the linear inverse problem where we wish to estimate a structured signal xx from its corrupted observations. When the problem is ill-posed, it is natural to make use of a convex function f()f(\cdot) that exploits the structure of the signal. For example, 1\ell_1 norm can be used for sparse signals. To carry out the estimation, we consider two well-known convex programs: 1) Second order cone program (SOCP), and, 2) Lasso. Assuming Gaussian measurements, we show that, if precise information about the value f(x)f(x) or the 2\ell_2-norm of the noise is available, one can do a particularly good job at estimation. In particular, the reconstruction error becomes proportional to the "sparsity" of the signal rather than the ambient dimension of the noise vector. We connect our results to existing works and provide a discussion on the relation of our results to the standard least-squares problem. Our error bounds are non-asymptotic and sharp, they apply to arbitrary convex functions and do not assume any distribution on the noise.

Keywords

Cite

@article{arxiv.1312.0641,
  title  = {Simple Bounds for Noisy Linear Inverse Problems with Exact Side Information},
  author = {Samet Oymak and Christos Thrampoulidis and Babak Hassibi},
  journal= {arXiv preprint arXiv:1312.0641},
  year   = {2013}
}

Comments

13 pages

R2 v1 2026-06-22T02:19:21.524Z