Estimation and Support Recovery with Exponential Weights

Stochastics Seminar
Thursday, September 20, 2012 - 3:05pm
1 hour (actually 50 minutes)
Skyles 006
Georgia Institute of Technology
In the context of a linear model with a sparse coefficient vector, sharp oracle inequalities have been established for the exponential weights concerning the prediction problem. We show that such methods also succeed at variable selection and estimation under near minimum condition on the design matrix, instead of much stronger assumptions required by other methods such as the Lasso or the Dantzig Selector. The same analysis yields consistency results for Bayesian methods and BIC-type variable selection under similar conditions. Joint work with Ery Arias-Castro