Efficient second-order online kernel learning with adaptive embedding

Daniele Calandriello 1 Alessandro Lazaric 1 Michal Valko 1
1 SEQUEL - Sequential Learning
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Abstract : Online kernel learning (OKL) is a flexible framework to approach prediction problems, since the large approximation space provided by reproducing kernel Hilbert spaces can contain an accurate function for the problem. Nonetheless, optimizing over this space is computationally expensive. Not only first order methods accumulate O( sqrt T ) more loss than the optimal function, but the curse of kernelization results in a O(t) per step complexity. Second-order methods get closer to the optimum much faster, suffering only O( log(T)) regret, but second-order updates are even more expensive, with a O(t 2) per-step cost. Existing approximate OKL methods try to reduce this complexity either by limiting the Support Vectors (SV) introduced in the predictor, or by avoiding the kernelization process altogether using embedding. Nonetheless, as long as the size of the approximation space or the number of SV does not grow over time, an adversary can always exploit the approximation process. In this paper, we propose PROS-N-KONS, a method that combines Nystrom sketching to project the input point in a small, accurate embedded space, and performs efficient second-order updates in this space. The embedded space is continuously updated to guarantee that the embedding remains accurate, and we show that the per-step cost only grows with the effective dimension of the problem and not with T . Moreover, the second-order updated allows us to achieve the logarithmic regret. We empirically compare our algorithm on recent large-scales benchmarks and show it performs favorably.
Type de document :
Communication dans un congrès
Neural Information Processing Systems, 2017, Long Beach, United States
Liste complète des métadonnées

Littérature citée [24 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01643961
Contributeur : Michal Valko <>
Soumis le : mardi 21 novembre 2017 - 18:26:19
Dernière modification le : mardi 3 juillet 2018 - 11:23:27

Fichier

calandriello2017efficient.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01643961, version 1

Citation

Daniele Calandriello, Alessandro Lazaric, Michal Valko. Efficient second-order online kernel learning with adaptive embedding. Neural Information Processing Systems, 2017, Long Beach, United States. 〈hal-01643961〉

Partager

Métriques

Consultations de la notice

285

Téléchargements de fichiers

30