Improved loss bounds for multiple kernel learning.
Journal of Machine Learning Research
370 - 377.
We propose two new generalization error bounds for multiple kernel learning (MKL). First, using the bound of Srebro and Ben-David (2006) as a starting point, we derive a new version which uses a simple counting argument for the choice of kernels in order to generate a tighter bound when 1-norm regularization (sparsity) is imposed in the kernel learning problem. The second bound is a Rademacher complexity bound which is additive in the (logarithmic) kernel complexity and margin term. This dependence is superior to all previously published Rademacher bounds for learning a convex combination of kernels, including the recent bound of Cortes et al. (2010), which exhibits a multiplicative interaction. We illustrate the tightness of our bounds with simulations. Copyright 2011 by the authors.
|Title:||Improved loss bounds for multiple kernel learning|
|Open access status:||An open access publication|
|UCL classification:||UCL > School of BEAMS > Faculty of Engineering Science > Computer Science|
Archive Staff Only