Timezone: »

 
Poster
On model selection consistency of penalized M-estimators: a geometric theory
Jason D Lee · Yuekai Sun · Jonathan E Taylor

Sun Dec 08 02:00 PM -- 06:00 PM (PST) @ Harrah's Special Events Center, 2nd Floor
in Poster Session »

Penalized M-estimators are used in diverse areas of science and engineering to fit high-dimensional models with some low-dimensional structure. Often, the penalties are \emph{geometrically decomposable}, \ie\ can be expressed as a sum of (convex) support functions. We generalize the notion of irrepresentable to geometrically decomposable penalties and develop a general framework for establishing consistency and model selection consistency of M-estimators with such penalties. We then use this framework to derive results for some special cases of interest in bioinformatics and statistical learning.

[ PDF] 

Author Information

Jason D Lee (University of Southern California)
Yuekai Sun (Stanford University)
Jonathan E Taylor (Stanford University)

More from the Same Authors