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. © 2013 IEEE.
|Original language||English (US)|
|Title of host publication||2013 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013 - Proceedings|
|State||Published - Dec 1 2013|