Ensembles of Kernel Predictors

Corinna Cortes, Mehryar Mohri, Afshin Rostamizadeh
Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence, PMLR R9:173-180, 2011.

Abstract

This paper examines the problem of learning with a finite and possibly large set of p base kernels. It presents a theoretical and empirical analysis of an approach addressing this problem based on ensembles of kernel predictors. This includes novel theoretical guarantees based on the Rademacher complexity of the corresponding hypothesis sets, the introduction and analysis of a learning algorithm based on these hypothesis sets, and a series of experiments using ensembles of kernel predictors with several data sets. Both convex combinations of kernel-based hypotheses and more general Lq-regularized nonnegative combinations are analyzed. These theoretical, algorithmic, and empirical results are compared with those achieved by using learning kernel techniques, which can be viewed as another approach for solving the same problem.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR9-cortes11a, title = {Ensembles of Kernel Predictors}, author = {Cortes, Corinna and Mohri, Mehryar and Rostamizadeh, Afshin}, booktitle = {Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence}, pages = {173--180}, year = {2011}, editor = {Cozman, Fabio and Pfeffer, Avi}, volume = {R9}, series = {Proceedings of Machine Learning Research}, month = {14--17 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r9/main/assets/cortes11a/cortes11a.pdf}, url = {https://proceedings.mlr.press/r9/cortes11a.html}, abstract = {This paper examines the problem of learning with a finite and possibly large set of p base kernels. It presents a theoretical and empirical analysis of an approach addressing this problem based on ensembles of kernel predictors. This includes novel theoretical guarantees based on the Rademacher complexity of the corresponding hypothesis sets, the introduction and analysis of a learning algorithm based on these hypothesis sets, and a series of experiments using ensembles of kernel predictors with several data sets. Both convex combinations of kernel-based hypotheses and more general Lq-regularized nonnegative combinations are analyzed. These theoretical, algorithmic, and empirical results are compared with those achieved by using learning kernel techniques, which can be viewed as another approach for solving the same problem.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Ensembles of Kernel Predictors %A Corinna Cortes %A Mehryar Mohri %A Afshin Rostamizadeh %B Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2011 %E Fabio Cozman %E Avi Pfeffer %F pmlr-vR9-cortes11a %I PMLR %P 173--180 %U https://proceedings.mlr.press/r9/cortes11a.html %V R9 %X This paper examines the problem of learning with a finite and possibly large set of p base kernels. It presents a theoretical and empirical analysis of an approach addressing this problem based on ensembles of kernel predictors. This includes novel theoretical guarantees based on the Rademacher complexity of the corresponding hypothesis sets, the introduction and analysis of a learning algorithm based on these hypothesis sets, and a series of experiments using ensembles of kernel predictors with several data sets. Both convex combinations of kernel-based hypotheses and more general Lq-regularized nonnegative combinations are analyzed. These theoretical, algorithmic, and empirical results are compared with those achieved by using learning kernel techniques, which can be viewed as another approach for solving the same problem. %Z Reissued by PMLR on 04 October 2026.
APA
Cortes, C., Mohri, M. & Rostamizadeh, A.. (2011). Ensembles of Kernel Predictors. Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R9:173-180 Available from https://proceedings.mlr.press/r9/cortes11a.html. Reissued by PMLR on 04 October 2026.

Related Material