Second-Order Kernel Online Convex Optimization with Adaptive Sketching

1 SEQUEL - Sequential Learning
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Abstract : Kernel online convex optimization (KOCO) is a framework combining the expressiveness of non-parametric kernel models with the regret guarantees of online learning. First-order KOCO methods such as functional gradient descent require only $O(t)$ time and space per iteration, and, when the only information on the losses is their convexity, achieve a minimax optimal $O(\sqrt{T})$ regret. Nonetheless, many common losses in kernel problems, such as squared loss, logistic loss, and squared hinge loss posses stronger curvature that can be exploited. In this case, second-order KOCO methods achieve $O(\log(\Det(K)))$ regret, which we show scales as $O(deff \log T)$, where $deff$ is the effective dimension of the problem and is usually much smaller than $O(\sqrt{T})$. The main drawback of second-order methods is their much higher $O(t^2)$ space and time complexity. In this paper, we introduce kernel online Newton step (KONS), a new second-order KOCO method that also achieves $O(deff\log T)$ regret. To address the computational complexity of second-order methods, we introduce a new matrix sketching algorithm for the kernel matrix~$K$, and show that for a chosen parameter $\gamma \leq 1$ our Sketched-KONS reduces the space and time complexity by a factor of $\gamma^2$ to $O(t^2\gamma^2)$ space and time per iteration, while incurring only $1/\gamma$ times more regret.
Type de document :
Communication dans un congrès
International Conference on Machine Learning, 2017, Sydney, Australia

Littérature citée [28 références]

https://hal.inria.fr/hal-01537799
Contributeur : Michal Valko <>
Soumis le : mardi 13 juin 2017 - 03:04:48
Dernière modification le : mercredi 21 février 2018 - 12:06:24
Document(s) archivé(s) le : mardi 12 décembre 2017 - 12:03:21

Fichier

calandriello2017second-order.p...
Fichiers produits par l'(les) auteur(s)

Identifiants

• HAL Id : hal-01537799, version 1

Citation

Daniele Calandriello, Alessandro Lazaric, Michal Valko. Second-Order Kernel Online Convex Optimization with Adaptive Sketching. International Conference on Machine Learning, 2017, Sydney, Australia. 〈hal-01537799〉

Métriques

Consultations de la notice

168

Téléchargements de fichiers