WSEAS Transactions on Mathematics
Print ISSN: 1109-2769, E-ISSN: 2224-2880
Volume 14, 2015
The Learning Rate of Vector-Valued Ranking with Least Square Loss
Authors: , ,
Abstract: In the present paper, we give an investigation on the quantitative convergence analysis of the kernel regularized vector ranking with least square loss. We present with Gȃteaux derivative the qualitative relation between the solution and the hiding distribution and quantitatively show the robustness for the solution. Finally, we provide a learning rate in terms of the approximation ability and capacity of the involved vector-valued RKHS.