Information Theoretic Limits for Linear Prediction with Graph-Structured Sparsity

01/26/2017
by   Adarsh Barik, et al.
0

We analyze the necessary number of samples for sparse vector recovery in a noisy linear prediction setup. This model includes problems such as linear regression and classification. We focus on structured graph models. In particular, we prove that sufficient number of samples for the weighted graph model proposed by Hegde and others is also necessary. We use the Fano's inequality on well constructed ensembles as our main tool in establishing information theoretic lower bounds.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset