Monte Carlo with kernel-based Gibbs measures: Guarantees for probabilistic herding - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2024

Monte Carlo with kernel-based Gibbs measures: Guarantees for probabilistic herding

Résumé

Kernel herding belongs to a family of deterministic quadratures that seek to minimize the worst-case integration error over a reproducing kernel Hilbert space (RKHS). In spite of strong experimental support, it has revealed difficult to prove that this worst-case error decreases at a faster rate than the standard square root of the number of quadrature nodes, at least in the usual case where the RKHS is infinite-dimensional. In this theoretical paper, we study a joint probability distribution over quadrature nodes, whose support tends to minimize the same worst-case error as kernel herding. We prove that it does outperform i.i.d. Monte Carlo, in the sense of coming with a tighter concentration inequality on the worst-case integration error. While not improving the rate yet, this demonstrates that the mathematical tools of the study of Gibbs measures can help understand to what extent kernel herding and its variants improve on computationally cheaper methods. Moreover, we provide early experimental evidence that a faster rate of convergence, though not worst-case, is likely.
Fichier principal
Vignette du fichier
2402.11736.pdf (1.26 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04468785 , version 1 (20-02-2024)

Identifiants

Citer

Martin Rouault, Rémi Bardenet, Mylène Maïda. Monte Carlo with kernel-based Gibbs measures: Guarantees for probabilistic herding. 2024. ⟨hal-04468785⟩
10 Consultations
5 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More