Leveraging PAC-Bayes Theory and Gibbs Distributions for Generalization Bounds with Complexity Measures - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

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

Résumé

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.

Dates et versions

hal-04473777 , version 1 (22-02-2024)

Licence

Paternité

Identifiants

Citer

Paul Viallard, Rémi Emonet, Amaury Habrard, Emilie Morvant, Valentina Zantedeschi. Leveraging PAC-Bayes Theory and Gibbs Distributions for Generalization Bounds with Complexity Measures. AISTATS 2024 - 27th International Conference on Artificial Intelligence and Statistics, May 2024, Valencia, Spain. ⟨hal-04473777⟩
12 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More