Answers are grounded in this paper and cite their sources.
In Bora et al. (2017), a mathematical framework was developed for compressed sensing guarantees in the setting where the measurement matrix is Gaussian and the signal structure is the range of a generative neural network (GNN). The problem of compressed sensing with GNNs has since been extensively analyzed when the measurement matrix and/or network weights follow a subgaussian distribution. We move beyond the subgaussian assumption, to measurement matrices that are derived by sampling uniformly at random rows of a unitary matrix (including subsampled Fourier measurements as a special case). Specifically, we prove the first known restricted isometry guarantee for generative compressed sensing (GCS) with subsampled isometries, and provide recovery bounds with nearly order-optimal sample complexity, addressing an open problem of (Scarlett et al., 2022, p. 10). Recovery efficacy is characterized by thecoherence, a new parameter, which measures the interplay between the range of the network and the measurement matrix. Our approach relies on subspace counting arguments and ideas central to high-dimensional probability. Furthermore, we propose a regularization strategy for training GNNs to have favourable coherence with the measurement operator. We provide compelling numerical simulations that support this regularized training strategy: our strategy yields low coherence networks that require fewer measurements for signal recovery. This, together with our theoretical results, supports coherence as a natural quantity for characterizing GCS with subsampled isometries.
No takes yet. Share an insight, caveat, or question.
Berk et al. (2022) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: