Risk Bounds for Randomized Sample Compressed Classifiers
Mohak Shah · 2008
We derive risk bounds for the randomized classifiers in Sample Compression set-ting where the classifier-specification utilizes two sources of information viz. the compression set and the message string. By extending the recently proposed Oc-cam’s Hammer principle to the data-dependent settings, we derive point-wise ver-sions of the bounds on the stochastic sample compressed classifiers and also re-cover the corresponding classical PAC-Bayes bound. We further show how these compare favorably to the existing results. 1