Unknown sparsity in compressed sensing: Denoising and inference

TL;DR

This paper introduces a new deconvolution-based method for estimating unknown sparsity levels in compressed sensing, providing sharper theoretical guarantees and wider applicability than previous approaches.

Contribution

It proposes a family of entropy-based sparsity measures and estimators with dimension-free convergence rates, bridging the gap between theory and practical sparsity estimation in CS.

Findings

Estimator $ ilde{s}_q(x)$ achieves $1/\sqrt{n}$ convergence rate.

The method applies to various sparsity measures including $ orm{x}_0$ and $ orm{x}_1^2/ orm{x}_2^2$.

Connections established to Basis Pursuit Denoising, Lasso, and deterministic measurement matrices.

Abstract

The theory of Compressed Sensing (CS) asserts that an unknown signal $x\in\mathbb{R}^p$ can be accurately recovered from an underdetermined set of $n$ linear measurements with $n\ll p$, provided that $x$ is sufficiently sparse. However, in applications, the degree of sparsity $\|x\|_0$ is typically unknown, and the problem of directly estimating $\|x\|_0$ has been a longstanding gap between theory and practice. A closely related issue is that $\|x\|_0$ is a highly idealized measure of sparsity, and for real signals with entries not equal to 0, the value $\|x\|_0=p$ is not a useful description of compressibility. In our previous conference paper [Lop13] that examined these problems, we considered an alternative measure of "soft" sparsity, $\|x\|_1^2/\|x\|_2^2$, and designed a procedure to estimate $\|x\|_1^2/\|x\|_2^2$ that does not rely on sparsity assumptions. The present work offers a new deconvolution-based method for estimating unknown sparsity, which has wider applicability and sharper theoretical guarantees. In particular, we introduce a family of entropy-based sparsity measures $s_q(x):=\big(\frac{\|x\|_q}{\|x\|_1}\big)^{\frac{q}{1-q}}$ parameterized by $q\in[0,\infty]$. This family interpolates between $\|x\|_0=s_0(x)$ and $\|x\|_1^2/\|x\|_2^2=s_2(x)$ as $q$ ranges over $[0,2]$. For any $q\in (0,2]\setminus\{1\}$, we propose an estimator $\hat{s}_q(x)$ whose relative error converges at the dimension-free rate of $1/\sqrt{n}$, even when $p/n\to\infty$. Our main results also describe the limiting distribution of $\hat{s}_q(x)$, as well as some connections to Basis Pursuit Denosing, the Lasso, deterministic measurement matrices, and inference problems in CS.