Leveraging PAC-Bayes Theory and Gibbs Distributions for Generalization Bounds with Complexity Measures

arXiv:2402.13285v1 Announce Type: cross
Abstract: In statistical learning theory, a generalization bound usually involves a complexity measure imposed by the considered theoretical framework. This limits the scope of such bounds, as other forms of capacity measures or regularizations are used in algorithms. In this paper, we leverage the framework of disintegrated PAC-Bayes bounds to derive a general generalization bound instantiable with arbitrary complexity measures. One trick to prove such a result involves considering a commonly used family of distributions: the …

abstract algorithms arxiv bayes capacity complexity cs.lg forms framework gibbs paper statistical stat.ml theory type