Solving $\ell^p\!$-norm regularization with tensor kernels
This addresses a computational bottleneck in machine learning for researchers and practitioners working with non-Hilbert regularization, though it appears incremental.
The paper tackles the problem of efficiently solving nonparametric extensions of ℓ^p-regularized learning methods by proposing a fast dual algorithm using tensor kernels, with numerical experiments confirming its effectiveness.
In this paper, we discuss how a suitable family of tensor kernels can be used to efficiently solve nonparametric extensions of $\ell^p$ 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.