Abstract | ||
---|---|---|
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}. |
Year | Venue | Keywords |
---|---|---|
2009 | international conference on machine learning | convex combination,artificial intelligent |
Field | DocType | Volume |
Discrete mathematics,Convex combination,Rademacher complexity,Regularization (mathematics),Artificial intelligence,Generalization error,Combinatorial analysis,Linear function,Machine learning,Mathematics | Journal | abs/0912.3 |
Citations | PageRank | References |
51 | 1.94 | 21 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Corinna Cortes | 1 | 6574 | 1120.50 |
Mehryar Mohri | 2 | 4502 | 448.21 |
Afshin Rostamizadeh | 3 | 911 | 44.15 |