Two-stage learning kernel algorithms

Corinna Cortes, Mehryar Mohri, Afshin Rostamizadeh

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

Abstract

This paper examines two-stage techniques for learning kernels based on a notion of alignment. It presents a number of novel theoretical, algorithmic, and empirical results for alignment- based techniques. Our results build on previous work by Cristianini et al. (2001), but we adopt a different definition of kernel alignment and significantly extend that work in several directions: we give a novel and simple concentration bound for alignment between kernel matrices; show the existence of good predictors for kernels with high alignment, both for classification and for regression; give algorithms for learning a maximum alignment kernel by showing that the problem can be reduced to a simple QP; and report the results of extensive experiments with this alignment-based method in classification and regression tasks, which show an improvement both over the uniform combination of kernels and over other state-of-the-art learning kernel methods.

Original languageEnglish (US)
Title of host publicationICML 2010 - Proceedings, 27th International Conference on Machine Learning
Pages239-246
Number of pages8
StatePublished - 2010
Event27th International Conference on Machine Learning, ICML 2010 - Haifa, Israel
Duration: Jun 21 2010Jun 25 2010

Other

Other27th International Conference on Machine Learning, ICML 2010
CountryIsrael
CityHaifa
Period6/21/106/25/10

Fingerprint

Learning algorithms
regression
learning method
learning
experiment
Experiments

ASJC Scopus subject areas

  • Artificial Intelligence
  • Education

Cite this

Cortes, C., Mohri, M., & Rostamizadeh, A. (2010). Two-stage learning kernel algorithms. In ICML 2010 - Proceedings, 27th International Conference on Machine Learning (pp. 239-246)

Two-stage learning kernel algorithms. / Cortes, Corinna; Mohri, Mehryar; Rostamizadeh, Afshin.

ICML 2010 - Proceedings, 27th International Conference on Machine Learning. 2010. p. 239-246.

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

Cortes, C, Mohri, M & Rostamizadeh, A 2010, Two-stage learning kernel algorithms. in ICML 2010 - Proceedings, 27th International Conference on Machine Learning. pp. 239-246, 27th International Conference on Machine Learning, ICML 2010, Haifa, Israel, 6/21/10.
Cortes C, Mohri M, Rostamizadeh A. Two-stage learning kernel algorithms. In ICML 2010 - Proceedings, 27th International Conference on Machine Learning. 2010. p. 239-246
Cortes, Corinna ; Mohri, Mehryar ; Rostamizadeh, Afshin. / Two-stage learning kernel algorithms. ICML 2010 - Proceedings, 27th International Conference on Machine Learning. 2010. pp. 239-246
@inproceedings{8ed96aa0ee9a4887a48239d403e11e8c,
title = "Two-stage learning kernel algorithms",
abstract = "This paper examines two-stage techniques for learning kernels based on a notion of alignment. It presents a number of novel theoretical, algorithmic, and empirical results for alignment- based techniques. Our results build on previous work by Cristianini et al. (2001), but we adopt a different definition of kernel alignment and significantly extend that work in several directions: we give a novel and simple concentration bound for alignment between kernel matrices; show the existence of good predictors for kernels with high alignment, both for classification and for regression; give algorithms for learning a maximum alignment kernel by showing that the problem can be reduced to a simple QP; and report the results of extensive experiments with this alignment-based method in classification and regression tasks, which show an improvement both over the uniform combination of kernels and over other state-of-the-art learning kernel methods.",
author = "Corinna Cortes and Mehryar Mohri and Afshin Rostamizadeh",
year = "2010",
language = "English (US)",
isbn = "9781605589077",
pages = "239--246",
booktitle = "ICML 2010 - Proceedings, 27th International Conference on Machine Learning",

}

TY - GEN

T1 - Two-stage learning kernel algorithms

AU - Cortes, Corinna

AU - Mohri, Mehryar

AU - Rostamizadeh, Afshin

PY - 2010

Y1 - 2010

N2 - This paper examines two-stage techniques for learning kernels based on a notion of alignment. It presents a number of novel theoretical, algorithmic, and empirical results for alignment- based techniques. Our results build on previous work by Cristianini et al. (2001), but we adopt a different definition of kernel alignment and significantly extend that work in several directions: we give a novel and simple concentration bound for alignment between kernel matrices; show the existence of good predictors for kernels with high alignment, both for classification and for regression; give algorithms for learning a maximum alignment kernel by showing that the problem can be reduced to a simple QP; and report the results of extensive experiments with this alignment-based method in classification and regression tasks, which show an improvement both over the uniform combination of kernels and over other state-of-the-art learning kernel methods.

AB - This paper examines two-stage techniques for learning kernels based on a notion of alignment. It presents a number of novel theoretical, algorithmic, and empirical results for alignment- based techniques. Our results build on previous work by Cristianini et al. (2001), but we adopt a different definition of kernel alignment and significantly extend that work in several directions: we give a novel and simple concentration bound for alignment between kernel matrices; show the existence of good predictors for kernels with high alignment, both for classification and for regression; give algorithms for learning a maximum alignment kernel by showing that the problem can be reduced to a simple QP; and report the results of extensive experiments with this alignment-based method in classification and regression tasks, which show an improvement both over the uniform combination of kernels and over other state-of-the-art learning kernel methods.

UR - http://www.scopus.com/inward/record.url?scp=77956505061&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956505061&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:77956505061

SN - 9781605589077

SP - 239

EP - 246

BT - ICML 2010 - Proceedings, 27th International Conference on Machine Learning

ER -