TY - GEN
T1 - Sparse signal recovery using Markov Random Fields
AU - Cevher, Volkan
AU - Duarte, Marco F.
AU - Hegde, Chinmay
AU - Baraniuk, Richard G.
PY - 2009
Y1 - 2009
N2 - Compressive Sensing (CS) combines sampling and compression into a single sub- Nyquist linear measurement process for sparse and compressible signals. In this paper, we extend the theory of CS to include signals that are concisely represented in terms of a graphicalmodel. In particular, we use Markov Random Fields (MRFs) to represent sparse signals whose nonzero coefficients are clustered. Our new model-based recovery algorithm, dubbed Lattice Matching Pursuit (LaMP), stably recovers MRF-modeled signals using many fewer measurements and computations than the current state-of-the-art algorithms.
AB - Compressive Sensing (CS) combines sampling and compression into a single sub- Nyquist linear measurement process for sparse and compressible signals. In this paper, we extend the theory of CS to include signals that are concisely represented in terms of a graphicalmodel. In particular, we use Markov Random Fields (MRFs) to represent sparse signals whose nonzero coefficients are clustered. Our new model-based recovery algorithm, dubbed Lattice Matching Pursuit (LaMP), stably recovers MRF-modeled signals using many fewer measurements and computations than the current state-of-the-art algorithms.
UR - http://www.scopus.com/inward/record.url?scp=84858788674&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84858788674&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84858788674
SN - 9781605609492
T3 - Advances in Neural Information Processing Systems 21 - Proceedings of the 2008 Conference
SP - 257
EP - 264
BT - Advances in Neural Information Processing Systems 21 - Proceedings of the 2008 Conference
PB - Neural Information Processing Systems
T2 - 22nd Annual Conference on Neural Information Processing Systems, NIPS 2008
Y2 - 8 December 2008 through 11 December 2008
ER -