Ensembles of kernel predictors

Corinna Cortes, Mehryar Mohri, Afshin Rostamizadeh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish (US)
Title of host publicationProceedings of the 27th Conference on Uncertainty in Artificial Intelligence, UAI 2011
Pages145-152
Number of pages8
StatePublished - 2011
Event27th Conference on Uncertainty in Artificial Intelligence, UAI 2011 - Barcelona, Spain
Duration: Jul 14 2011Jul 17 2011

Other

Other27th Conference on Uncertainty in Artificial Intelligence, UAI 2011
CountrySpain
CityBarcelona
Period7/14/117/17/11

Fingerprint

Learning algorithms
Predictors
Ensemble
kernel
Experiments
Convex Combination
Empirical Analysis
Large Set
Learning Algorithm
Theoretical Analysis
Non-negative
Series
Experiment
Learning

ASJC Scopus subject areas

  • Artificial Intelligence
  • Applied Mathematics

Cite this

Cortes, C., Mohri, M., & Rostamizadeh, A. (2011). Ensembles of kernel predictors. In Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence, UAI 2011 (pp. 145-152)

Ensembles of kernel predictors. / Cortes, Corinna; Mohri, Mehryar; Rostamizadeh, Afshin.

Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence, UAI 2011. 2011. p. 145-152.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Cortes, C, Mohri, M & Rostamizadeh, A 2011, Ensembles of kernel predictors. in Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence, UAI 2011. pp. 145-152, 27th Conference on Uncertainty in Artificial Intelligence, UAI 2011, Barcelona, Spain, 7/14/11.
Cortes C, Mohri M, Rostamizadeh A. Ensembles of kernel predictors. In Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence, UAI 2011. 2011. p. 145-152
Cortes, Corinna ; Mohri, Mehryar ; Rostamizadeh, Afshin. / Ensembles of kernel predictors. Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence, UAI 2011. 2011. pp. 145-152
@inproceedings{7073e303cbfd459492d57d864b21d025,
title = "Ensembles of kernel predictors",
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.",
author = "Corinna Cortes and Mehryar Mohri and Afshin Rostamizadeh",
year = "2011",
language = "English (US)",
pages = "145--152",
booktitle = "Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence, UAI 2011",

}

TY - GEN

T1 - Ensembles of kernel predictors

AU - Cortes, Corinna

AU - Mohri, Mehryar

AU - Rostamizadeh, Afshin

PY - 2011

Y1 - 2011

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=80053152753&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053152753&partnerID=8YFLogxK

M3 - Conference contribution

SP - 145

EP - 152

BT - Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence, UAI 2011

ER -