A Note on Compressed Sensing of Structured Sparse Wavelet Coefficients From Subsampled Fourier Measurements

Abstract

We consider signal recovery from Fourier measurements using compressed sensing (CS) with wavelets. For discrete signals with structured sparse Haar wavelet coefficients, we give the first proof of near-optimal recovery from discrete Fourier samples taken according to an appropriate variable density sampling scheme. Crucially, in taking into account such structured sparsity—known as sparsity in levels—as opposed to just sparsity, this result yields recovery guarantees that agree with the empirically observed recovery properties of CS in this setting. This result complements a recent theorem in Adcock et al. [Breaking the coherence barrier: A new theory for compressed sensing, arXiv preprint arXiv: 1302.0561, 2014.], which addressed the case of continuous time signals. Moreover, we provide a significantly shorter and more expositional argument, which clearly illustrates the key factors governing recovery in this setting: namely the division of frequency space into dyadic bands corresponding to wavelet scales, the near-block diagonality of the Fourier/wavelet cross-Gramian matrix, and the structured sparsity of wavelet coefficients.