Pré-Publication, Document De Travail Année : 2025

Minimax Adaptive Online Nonparametric Regression over Besov Spaces

Résumé

We study online adversarial regression with convex losses against a rich class of continuous yet highly irregular prediction rules, modeled by Besov spaces $B_{pq}^s$ with general parameters $1 \leq p,q \leq \infty$ and smoothness $s > d/p$. We introduce an adaptive wavelet-based algorithm that performs sequential prediction without prior knowledge of $(s,p,q)$, and establish minimax-optimal regret bounds against any comparator in $B_{pq}^s$. We further design a locally adaptive extension capable of dynamically tracking spatially inhomogeneous smoothness. This adaptive mechanism adjusts the resolution of the predictions over both time and space, yielding refined regret bounds in terms of local regularity. Consequently, in heterogeneous environments, our adaptive guarantees can significantly surpass those obtained by standard global methods.

Fichier principal
Vignette du fichier
main_preprint.pdf (599.87 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05082189 , version 1 (23-05-2025)
hal-05082189 , version 2 (16-09-2025)

Licence

Identifiants

  • HAL Id : hal-05082189 , version 1

Citer

Paul Liautaud, Pierre Gaillard, Olivier Wintenberger. Minimax Adaptive Online Nonparametric Regression over Besov Spaces. 2025. ⟨hal-05082189v1⟩
380 Consultations
356 Téléchargements

Partager

  • More