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.
Solving l(p)-norm regularization with tensor kernels / Salzo, S; Suykens, Jak; Rosasco, L. - 84:(2018). (Intervento presentato al convegno 21st International Conference on Artificial Intelligence and Statistics (AISTATS) tenutosi a Lanzarote, SPAIN).
Solving l(p)-norm regularization with tensor kernels
Salzo S;
2018
Abstract
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.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
