preprint · arXiv (Cornell University) · 2012

Sparsity in multiple kernel learning

Koltchinskii, Vladimir, Yuan, Ming

Cited by 0Open access

Abstract

The problem of multiple kernel learning based on penalized empirical risk minimization is discussed. The complexity penalty is determined jointly by the empirical $L_2$ norms and the reproducing kernel Hilbert space (RKHS) norms induced by the kernels with a data-driven choice of regularization parameters. The main focus is on the case when the total number of kernels is large, but only a relatively small number of them is needed to represent the target function, so that the problem is sparse. The goal is to establish oracle inequalities for the excess risk of the resulting prediction rule showing that the method is adaptive both to the unknown design distribution and to the sparsity of the problem.

Cite this paper

APA 7

Koltchinskii, V., & Yuan, M. (2012). Sparsity in multiple kernel learning. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1211.2998

MLA 9

Koltchinskii, Vladimir, and Ming Yuan. “Sparsity in multiple kernel learning.” arXiv (Cornell University), 2012, https://doi.org/10.48550/arxiv.1211.2998.

Chicago

Koltchinskii, Vladimir, and Ming Yuan. 2012. “Sparsity in multiple kernel learning.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1211.2998.

Harvard

Koltchinskii, V. and Yuan, M. (2012) ‘Sparsity in multiple kernel learning’, arXiv (Cornell University). Available at: https://doi.org/10.48550/arxiv.1211.2998.

BibTeX

@misc{koltchinskii2012sparsity,
  title = {{Sparsity in multiple kernel learning}},
  author = {Koltchinskii, Vladimir and Yuan, Ming},
  journal = {arXiv (Cornell University)},
  year = {2012},
  doi = {10.48550/arxiv.1211.2998}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.