Skip to yearly menu bar Skip to main content


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

Paul Viallard · RĂ©mi Emonet · Amaury Habrard · Emilie Morvant · Valentina Zantedeschi

MR1 & MR2 - Number 23
[ ]
Sat 4 May 6 a.m. PDT — 8:30 a.m. PDT


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 Gibbs distributions. Our bound stands in probability jointly over the hypothesis and the learning sample, which allows the complexity to be adapted to the generalization gap as it can be customized to fit both the hypothesis class and the task.

Live content is unavailable. Log in and register to view live content