Minimax risk for Poisson compressed sensing

This paper describes performance bounds for compressed sensing in the presence of Poisson noise and shows that, for sparse or compressible signals, they are within a log factor of known lower bounds on the risk. The signal-independent and bounded noise models used in the literature to analyze the performance of compressed sensing do not accurately model the effects of Poisson noise. However, Poisson noise is an appropriate noise model for a variety of applications, including low-light imaging, in which sensing hardware is large or expensive and limiting the number of measurements collected is important. In this paper, we describe how a feasible sensing matrix can be constructed and prove a concentration-of-measure inequality for these matrices. We then show that minimizing an objective function consisting of a negative Poisson log likelihood term and a penalty term which could be used as a measure of signal sparsity results in near-minimax rates of error decay.