Reconstruction of Gaussian mixture models from compressive measurements: A phase transition view
Francesco Renna, Robert Calderbank, Lawrence Carin, Miguel R. D. Rodrigues · 2013
We characterize the minimum number of measurements needed to drive to zero the minimum mean squared error (MMSE) of Gaussian mixture model (GMM) input signals in the low-noise regime. The result also hints at almost phase-transition optimal recovery procedures based on a classification and reconstruction approach.