# Simpler PAC-Bayesian Bounds for Hostile Data

23 Oct 2016Pierre AlquierBenjamin Guedj

PAC-Bayesian learning bounds are of the utmost interest to the learning community. Their role is to connect the generalization ability of an aggregation distribution $\rho$ to its empirical risk and to its Kullback-Leibler divergence with respect to some prior distribution $\pi$... (read more)

PDF Abstract

No code implementations yet. Submit your code now