Reconstruction of Gaussian mixture models from compressive measurements: A phase transition view


Journal Article

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.

Full Text

Duke Authors

Cited Authors

  • Renna, F; Calderbank, R; Carin, L; Rodrigues, MRD

Published Date

  • December 1, 2013

Published In

  • 2013 Ieee Global Conference on Signal and Information Processing, Globalsip 2013 Proceedings

Start / End Page

  • 628 -

Digital Object Identifier (DOI)

  • 10.1109/GlobalSIP.2013.6736965

Citation Source

  • Scopus