Multi-class classification with maximum margin multiple kernel

Corinna Cortes, Mehryar Mohri, Afshin Rostamizadeh

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

Abstract

We present a new algorithm for multi-class classification with multiple kernels. Our algorithm is based on a natural notion of the multi-class margin of a kernel. We show that larger values of this quantity guarantee the existence of an accurate multi-class predictor and also define a family of multiple kernel algorithms based on the maximization of the multi-class margin of a kernel (M3K). We present an extensive theoretical analysis in support of our algorithm, including novel multi-class Rademacher complexity margin bounds. Finally, we also report the results of a series of experiments with several data sets, including comparisons where we improve upon the performance of state-of-the-art algorithms both in binary and multi-class classification with multiple kernels.

Original languageEnglish (US)
Title of host publication30th International Conference on Machine Learning, ICML 2013
PublisherInternational Machine Learning Society (IMLS)
Pages1083-1091
Number of pages9
EditionPART 2
StatePublished - 2013
Event30th International Conference on Machine Learning, ICML 2013 - Atlanta, GA, United States
Duration: Jun 16 2013Jun 21 2013

Other

Other30th International Conference on Machine Learning, ICML 2013
CountryUnited States
CityAtlanta, GA
Period6/16/136/21/13

Fingerprint

guarantee
experiment
performance
Values
Experiments

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Sociology and Political Science

Cite this

Cortes, C., Mohri, M., & Rostamizadeh, A. (2013). Multi-class classification with maximum margin multiple kernel. In 30th International Conference on Machine Learning, ICML 2013 (PART 2 ed., pp. 1083-1091). International Machine Learning Society (IMLS).

Multi-class classification with maximum margin multiple kernel. / Cortes, Corinna; Mohri, Mehryar; Rostamizadeh, Afshin.

30th International Conference on Machine Learning, ICML 2013. PART 2. ed. International Machine Learning Society (IMLS), 2013. p. 1083-1091.

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

Cortes, C, Mohri, M & Rostamizadeh, A 2013, Multi-class classification with maximum margin multiple kernel. in 30th International Conference on Machine Learning, ICML 2013. PART 2 edn, International Machine Learning Society (IMLS), pp. 1083-1091, 30th International Conference on Machine Learning, ICML 2013, Atlanta, GA, United States, 6/16/13.
Cortes C, Mohri M, Rostamizadeh A. Multi-class classification with maximum margin multiple kernel. In 30th International Conference on Machine Learning, ICML 2013. PART 2 ed. International Machine Learning Society (IMLS). 2013. p. 1083-1091
Cortes, Corinna ; Mohri, Mehryar ; Rostamizadeh, Afshin. / Multi-class classification with maximum margin multiple kernel. 30th International Conference on Machine Learning, ICML 2013. PART 2. ed. International Machine Learning Society (IMLS), 2013. pp. 1083-1091
@inproceedings{e92ccb62383a4962a58a01df775b9259,
title = "Multi-class classification with maximum margin multiple kernel",
abstract = "We present a new algorithm for multi-class classification with multiple kernels. Our algorithm is based on a natural notion of the multi-class margin of a kernel. We show that larger values of this quantity guarantee the existence of an accurate multi-class predictor and also define a family of multiple kernel algorithms based on the maximization of the multi-class margin of a kernel (M3K). We present an extensive theoretical analysis in support of our algorithm, including novel multi-class Rademacher complexity margin bounds. Finally, we also report the results of a series of experiments with several data sets, including comparisons where we improve upon the performance of state-of-the-art algorithms both in binary and multi-class classification with multiple kernels.",
author = "Corinna Cortes and Mehryar Mohri and Afshin Rostamizadeh",
year = "2013",
language = "English (US)",
pages = "1083--1091",
booktitle = "30th International Conference on Machine Learning, ICML 2013",
publisher = "International Machine Learning Society (IMLS)",
edition = "PART 2",

}

TY - GEN

T1 - Multi-class classification with maximum margin multiple kernel

AU - Cortes, Corinna

AU - Mohri, Mehryar

AU - Rostamizadeh, Afshin

PY - 2013

Y1 - 2013

N2 - We present a new algorithm for multi-class classification with multiple kernels. Our algorithm is based on a natural notion of the multi-class margin of a kernel. We show that larger values of this quantity guarantee the existence of an accurate multi-class predictor and also define a family of multiple kernel algorithms based on the maximization of the multi-class margin of a kernel (M3K). We present an extensive theoretical analysis in support of our algorithm, including novel multi-class Rademacher complexity margin bounds. Finally, we also report the results of a series of experiments with several data sets, including comparisons where we improve upon the performance of state-of-the-art algorithms both in binary and multi-class classification with multiple kernels.

AB - We present a new algorithm for multi-class classification with multiple kernels. Our algorithm is based on a natural notion of the multi-class margin of a kernel. We show that larger values of this quantity guarantee the existence of an accurate multi-class predictor and also define a family of multiple kernel algorithms based on the maximization of the multi-class margin of a kernel (M3K). We present an extensive theoretical analysis in support of our algorithm, including novel multi-class Rademacher complexity margin bounds. Finally, we also report the results of a series of experiments with several data sets, including comparisons where we improve upon the performance of state-of-the-art algorithms both in binary and multi-class classification with multiple kernels.

UR - http://www.scopus.com/inward/record.url?scp=84897557328&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897557328&partnerID=8YFLogxK

M3 - Conference contribution

SP - 1083

EP - 1091

BT - 30th International Conference on Machine Learning, ICML 2013

PB - International Machine Learning Society (IMLS)

ER -