Error bounds for \(l^p\)-norm multiple kernel learning with least square loss (Q448851)

Summary: The problem of learning the kernel function with linear combinations of multiple kernels has attracted considerable attention recently in machine learning. Specially, by imposing an \(l^p\)-norm penalty on the kernel combination coefficient, multiple kernel learning (MKL) was proved useful and effective for theoretical analysis and practical applications. In this paper, we present a theoretical analysis on the approximation error and learning ability of the \(l^p\)-norm MKL. Our analysis shows explicit learning rates for \(l^p\)-norm MKL and demonstrates some notable advantages compared with traditional kernel-based learning algorithms where the kernel is fixed.