Idioma:

Multi-task Learning in vector-valued reproducing kernel Banach spaces with the ℓ1 norm

Lin, Rongrong ; Song, Guohui ; Zhang, Haizhang

Journal of Complexity, 2021-04, Vol.63, Article 101514 [Periódico revisado por pares]

Texto completo disponível

Citações Citado por

Título:
Multi-task Learning in vector-valued reproducing kernel Banach spaces with the ℓ1 norm
Autor: Lin, Rongrong ; Song, Guohui ; Zhang, Haizhang
Assuntos: Admissible multi-task kernels ; Lebesgue constants ; Representer theorems ; Reproducing kernel Banach spaces
É parte de: Journal of Complexity, 2021-04, Vol.63, Article 101514
Descrição: Targeting at sparse multi-task learning, we consider regularization models with an ℓ1 penalty on the coefficients of kernel functions. In order to provide a kernel method for this model, we construct a class of vector-valued reproducing kernel Banach spaces with the ℓ1 norm. The notion of multi-task admissible kernels is proposed so that the constructed spaces could have desirable properties including the crucial linear representer theorem. Such kernels are related to bounded Lebesgue constants of a kernel interpolation question. We study the Lebesgue constant of multi-task kernels and provide examples of admissible kernels. Furthermore, we present numerical experiments for both synthetic data and real-world benchmark data to demonstrate the advantages of the proposed construction and regularization models.
Editor: Elsevier Inc
Idioma: Inglês

Voltar para lista de resultados