About DCS-AMP

DCS-AMP is a Bayesian message passing algorithm that solves the dynamic compressed sensing (DCS) problem, in which a time-varying vector of noisy measurements, y(t), is acquired from a time-varying sparse signal vector, x(t), through the linear measurement process y(t) = A(t)x(t) + e(t), where A(t) is a measurement matrix (typically with more columns than rows), and e(t) is corrupting noise. The unique feature of the DCS problem is the assumption that the support (i.e., the locations of the non-zero entries) of x(t) varies slowly over time.

Benefits of DCS-AMP:
• DCS-AMP works really quickly, especially in high-dimensions!
• Performs soft estimation and support detection
• Model parameters learned automatically from data
• Performs near theoretical bounds for many problems
• Support for implicit matrix operators, e.g., FFTs

DCS-AMP has been implemented in MATLAB, and has been shown to work extremely quickly, requiring only simple matrix-vector products to perform its computations. Click here to try it out.

DCS-AMP: An algorithm for efficient high-dimensional inference in the dynamic compressed sensing (DCS) problem

Authors

• Justin Ziniel
• Philip Schniter

See Also:

• Nuit Blanche
• Rice CS Resources
• Modified-CS Homepage
• IPS Lab