A Note on the Efficient Evaluation of PAC-Bayes Bounds

09/12/2022
by   Felix Biggs, et al.
0

When utilising PAC-Bayes theory for risk certification, it is usually necessary to estimate and bound the Gibbs risk of the PAC-Bayes posterior. Many works in the literature employ a method for this which requires a large number of passes of the dataset, incurring high computational cost. This manuscript presents a very general alternative which makes computational savings on the order of the dataset size.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset