Accurate Prediction of Phase Transitions in Compressed Sensing via a Connection to Minimax Denoising

Abstract

Compressed sensing posits that, within limits, one can undersample a sparse signal and yet reconstruct it accurately. Knowing the precise limits to such undersampling is important both for theory and practice. We present a formula that characterizes the allowed undersampling of generalized sparse objects. The formula applies to Approximate Message Passing (AMP) algorithms for compressed sensing, which are here generalized to employ denoising operators besides the traditional scalar soft thresholding denoiser. This paper gives several examples including scalar denoisers not derived from convex penalization -- the firm shrinkage nonlinearity and the minimax nonlinearity -- and also nonscalar denoisers -- block thresholding, monotone regression, and total variation minimization. Let the variables eps = k/N and delta = n/N denote the generalized sparsity and undersampling fractions for sampling the k-generalized-sparse N-vector x_0 according to y=Ax_0. Here A is an n\times N measurement matrix whose entries are iid standard Gaussian. The formula states that the phase transition curve delta = delta(eps) separating successful from unsuccessful reconstruction of x_0 by AMP is given by: delta = M(eps| Denoiser), where M(eps| Denoiser) denotes the per-coordinate minimax mean squared error (MSE) of the specified, optimally-tuned denoiser in the directly observed problem y = x + z. In short, the phase transition of a noiseless undersampling problem is identical to the minimax MSE in a denoising problem.

71 pages, 32 pdf figures

References in corpus (7)

• Compressive Imaging using Approximate Message Passing and a Markov-Tree Prior
• Message-Passing Estimation from Quantized Samples
• Finite size scaling for the core of large random hypergraphs
• Block-length dependent thresholds in block-sparse compressed sensing
• Tight Measurement Bounds for Exact Recovery of Structured Sparse Signals
• Compressive Sensing over the Grassmann Manifold: a Unified Geometric Framework
• Improved Sparse Recovery Thresholds with Two-Step Reweighted ${\ell }_1$ Minimization

Cited by in corpus (3)

• Exact minimax estimation of the predictive density in sparse Gaussian models
• Maximin Analysis of Message Passing Algorithms for Recovering Block Sparse Signals
• On block coherence of frames