A Note on the PAC Bayesian Theorem

We prove general exponential moment inequalities for averages of [0,1]valued iid random variables and use them to tighten the PAC Bayesian Theorem. The logarithmic dependence on the sample count in the enumerator of the PAC Bayesian bound is halved.

• Type: Journal
• Year: 2004
• Where: CORR
• Authors: Andreas Maurer
• Keywords: CORR 2004, Education, Moment Inequalities, PAC Bayesian Theorem, Random Variables