Optimal learning rates of lplp-type multiple kernel learning under general conditions

One of the most promising learning kernel methods is the lplp-type multiple kernel learning proposed by Kloft et al. (2009). This method can adaptively select kernel function in supervised learning problems. The majority of the studies associated with generalization error have recently received wide attention in machine learning and statistics. The present study aims to establish a new generalization error bound under more general frameworks, in which the correlation among reproducing kernel Hilbert spaces (RKHSs) is considered, and the restriction of smooth condition on the target function is relaxed. In this case, the interaction between the estimation and approximation errors must be simultaneously regarded. In this investigation, optimal learning rates are derived by applying the local Rademacher complexity technique, which is given in terms of the capacity of RKHSs spanned by multi-kernels and target function regularity.