PAC-Bayes-Chernoff bounds for unbounded losses

We introduce a new PAC-Bayes oracle bound for unbounded losses. This result can be understood as a PAC-Bayesian version of the Cram\'er-Chernoff bound. The proof technique relies on controlling the tails of certain random variables involving the Cram\'er transform of the loss. We highlight several applications of the main theorem. First, we show that our result naturally allows exact optimization of the free parameter on many PAC-Bayes bounds. Second, we recover and generalize previous results. Finally, we show that our …

applications bayes bayesian cs.lg highlight loss losses oracle random show stat.ml theorem variables