Plug-And-Play Learned Gaussian-mixture Approximate Message Passing
This work provides an improved compressed sensing recovery algorithm for signal processing researchers, offering state-of-the-art performance across diverse data distributions.
This paper proposes Learned Gaussian-mixture Approximate Message Passing (L-GM-AMP), a plug-and-play compressed sensing recovery algorithm. It achieves state-of-the-art performance for various source priors without prior knowledge, by using a universal denoising function based on Gaussian-mixture modeling.
Deep unfolding showed to be a very successful approach for accelerating and tuning classical signal processing algorithms. In this paper, we propose learned Gaussian-mixture AMP (L-GM-AMP) - a plug-and-play compressed sensing (CS) recovery algorithm suitable for any i.i.d. source prior. Our algorithm builds upon Borgerding's learned AMP (LAMP), yet significantly improves it by adopting a universal denoising function within the algorithm. The robust and flexible denoiser is a byproduct of modelling source prior with a Gaussian-mixture (GM), which can well approximate continuous, discrete, as well as mixture distributions. Its parameters are learned using standard backpropagation algorithm. To demonstrate robustness of the proposed algorithm, we conduct Monte-Carlo (MC) simulations for both mixture and discrete distributions. Numerical evaluation shows that the L-GM-AMP algorithm achieves state-of-the-art performance without any knowledge of the source prior.