scientific article

zbMath1235.68128MaRDI QIDQ2880982

Andreas Argyriou, Massimiliano Pontil, Charles A. Micchelli

Publication date: 17 April 2012

Full work available at URL: http://www.jmlr.org/papers/v10/argyriou09a.html

Title: zbMATH Open Web Interface contents unavailable due to conflicting licenses.

zbMATH Keywords

regularizationkernel methodsmulti-task learningminimal norm interpolationmatrix learning

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) General nonlinear regression (62J02) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (20)

Generalized semi-inner products with applications to regularized learning ⋮ Learning with infinitely many features ⋮ Functional reproducing kernel Hilbert spaces for non-point-evaluation functional data ⋮ Nyström-based approximate kernel subspace learning ⋮ When is there a representer theorem? Nondifferentiable regularisers and Banach spaces ⋮ Decentralized learning over a network with Nyström approximation using SGD ⋮ Unnamed Item ⋮ Learning rates of multitask kernel methods ⋮ A duality approach to regularized learning problems in Banach spaces ⋮ Efficiently learning the preferences of people ⋮ Finite rank kernels for multi-task learning ⋮ Kernelization of matrix updates, when and how? ⋮ Generalized Mercer Kernels and Reproducing Kernel Banach Spaces ⋮ KOC+: kernel ridge regression based one-class classification using privileged information ⋮ A unifying representer theorem for inverse problems and machine learning ⋮ Unnamed Item ⋮ Learning with tensors: a framework based on convex optimization and spectral regularization ⋮ Regularized learning in Banach spaces as an optimization problem: representer theorems ⋮ System identification using kernel-based regularization: new insights on stability and consistency issues ⋮ When is there a representer theorem? Reflexive Banach spaces

This page was built for publication: