New generalization bounds for learning kernels
arXiv preprint arXiv:0912.3309, 2009•arxiv.org
This paper presents several novel generalization bounds for the problem of learning kernels
based on the analysis of the Rademacher complexity of the corresponding hypothesis sets.
Our bound for learning kernels with a convex combination of p base kernels has only a log
(p) dependency on the number of kernels, p, which is considerably more favorable than the
previous best bound given for the same problem. We also give a novel bound for learning
with a linear combination of p base kernels with an L_2 regularization whose dependency …
based on the analysis of the Rademacher complexity of the corresponding hypothesis sets.
Our bound for learning kernels with a convex combination of p base kernels has only a log
(p) dependency on the number of kernels, p, which is considerably more favorable than the
previous best bound given for the same problem. We also give a novel bound for learning
with a linear combination of p base kernels with an L_2 regularization whose dependency …
This paper presents several novel generalization bounds for the problem of learning kernels based on the analysis of the Rademacher complexity of the corresponding hypothesis sets. Our bound for learning kernels with a convex combination of p base kernels has only a log(p) dependency on the number of kernels, p, which is considerably more favorable than the previous best bound given for the same problem. We also give a novel bound for learning with a linear combination of p base kernels with an L_2 regularization whose dependency on p is only in p^{1/4}.
arxiv.org