Computer Science – Information Theory
Scientific paper
2012-02-08
Computer Science
Information Theory
17 pages, 3 figures. Submitted to IEEE Trans. Inform. Theory
Scientific paper
Suppose that we observe noisy linear measurements of an unknown signal that can be modeled as the sum of two component signals, each of which arises from a nonlinear sub-manifold of a high dimensional ambient space. We introduce SPIN, a first order projected gradient method to recover the signal components. Despite the nonconvex nature of the recovery problem and the possibility of underdetermined measurements, SPIN provably recovers the signal components, provided that the signal manifolds are incoherent and that the measurement operator satisfies a certain restricted isometry property. SPIN significantly extends the scope of current recovery models and algorithms for low dimensional linear inverse problems and matches (or exceeds) the current state of the art in terms of performance.
Baraniuk Richard G.
Hegde Chinmay
No associations
LandOfFree
Signal Recovery on Incoherent Manifolds does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Signal Recovery on Incoherent Manifolds, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Signal Recovery on Incoherent Manifolds will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-64039