Home » Publication » 27085

Dettaglio pubblicazione

2018, International Conference on Artificial Intelligence and Statistics (AISTATS), Pages - (volume: 84)

Solving l(p)-norm regularization with tensor kernels (04b Atto di convegno in volume)

Salzo S, Suykens Jak, Rosasco L

In this paper, we discuss how a suitable family of tensor kernels can be used to efficiently solve nonparametric extensions of l(p) regularized learning methods. Our main contribution is proposing a fast dual algorithm, and showing that it allows to solve the problem efficiently. Our results contrast recent findings suggesting kernel methods cannot be extended beyond Hilbert setting. Numerical experiments confirm the effectiveness of the method.
Gruppo di ricerca: Continuous Optimization
© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma