Localized Multiple Kernel Learning---A Convex Approach
This work addresses the need for more effective kernel-based learning methods in domains like computational biology and computer vision, though it appears incremental as it builds on existing multiple kernel learning frameworks.
The paper tackles the problem of improving prediction accuracy in multiple kernel learning by proposing a convex localized approach, achieving higher accuracies than global and non-convex local methods on real-world datasets from computational biology and computer vision.
We propose a localized approach to multiple kernel learning that can be formulated as a convex optimization problem over a given cluster structure. For which we obtain generalization error guarantees and derive an optimization algorithm based on the Fenchel dual representation. Experiments on real-world datasets from the application domains of computational biology and computer vision show that convex localized multiple kernel learning can achieve higher prediction accuracies than its global and non-convex local counterparts.