The following problem is considered: given a joint distribution PXY and an event E, bound PXY (E) in terms of PX PY (E) (where PX PY is the product of the marginals of PXY ) and a measure of dependence of X and Y . Such bounds have direct applications in the analysis of the generalization error of learning algorithms, where E represents a large error event and the measure of dependence controls the degree of overfitting. Herein, bounds are demonstrated using several information-theoretic metrics, in particular: mutual information, lautum information, maximal leakage, and J∞. The mutual information bound can outperform comparable bounds in the literature by an arbitrarily large factor.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.