Generalization Bounds on Multi-Kernel Learning with Mixed Datasets

This paper presents novel generalization bounds for the multi-kernel learning problem. Motivated by applications in sensor networks and spatial-temporal models, we assume that the dataset is mixed where each sample is taken from a finite pool of Markov chains. Our bounds for learning kernels admit O(√log m) dependency on the number of base kernels and O(1/√n) dependency on the number of training samples. However, some O(1/√n) terms are added to compensate for the dependency among samples compared with existing generalization bounds for multi-kernel learning with i.i.d. datasets.