[Ml-stat-talks] Wilks Statistics Seminar - Cun-Hui Zhang - Tomorrow, Feb 24 at 12:30 PM in Sherrerd 213
Ahmet Emre Barut
abarut at Princeton.EDU
Thu Feb 23 19:33:21 EST 2012
Tomorrow, Feb 24<x-apple-data-detectors://0>, we will have a talk by Prof. Cun-Hui Zhang from Rutgers University as part of the Wilks Statistics Seminar series. The talk is in Statlab (Sherrerd 213) at 12:30 PM<x-apple-data-detectors://1>.
Title: A General Theory of Concave Regularization for High Dimensional Sparse Estimation Problems<http://arxiv.org/pdf/1108.4988v2.pdf>
Abstract: Concave regularization methods provide natural procedures for sparse recovery. However, they are difficult to analyze in the high dimensional setting. Only recently a few sparse recovery results have been established for some specific local solutions obtained via specialized numerical procedures. Still, the fundamental relationship between these solutions such as whether they are identical or their relationship to the global minimizer of the underlying nonconvex formulation is unknown. The current paper fills this conceptual gap by presenting a general theoretical framework showing that under appropriate conditions, the global solution of nonconvex regularization leads to desirable recovery performance; moreover, under suitable conditions, the global solution corresponds to the unique sparse local solution, which can be obtained via different numerical procedures. Under this unified framework, we present an overview of existing results and discuss their connections. The unified view of this work leads to a more satisfactory treatment of concave high dimensional sparse estimation procedures, and serves as guideline for developing further numerical procedures for concave regularization.
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Ml-stat-talks