Article

Learning the kernel matrix in discriminant analysis via quadratically constrained quadratic programming

Authors:

Jianhui ChenAuthors Info & Claims

KDD '07: Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining

Pages 854 - 863

https://doi.org/10.1145/1281192.1281283

Published: 12 August 2007 Publication History

Abstract

The kernel function plays a central role in kernel methods. In this paper, we consider the automated learning of the kernel matrix over a convex combination of pre-specified kernel matrices in Regularized Kernel Discriminant Analysis (RKDA), which performs lineardiscriminant analysis in the feature space via the kernel trick. Previous studies have shown that this kernel learning problem can be formulated as a semidefinite program (SDP), which is however computationally expensive, even with the recent advances in interior point methods. Based on the equivalence relationship between RKDA and least square problems in the binary-class case, we propose a Quadratically Constrained Quadratic Programming (QCQP) formulation for the kernel learning problem, which can be solved more efficiently than SDP. While most existing work on kernel learning deal with binary-class problems only, we show that our QCQP formulation can be extended naturally to the multi-class case. Experimental results on both binary-class and multi-class benchmarkdata sets show the efficacy of the proposed QCQP formulations.

Supplementary Material

JPG File (p854-ye-200.jpg)

Download
7.43 KB

JPG File (p854-ye-768.jpg)

Download
9.18 KB

Low Resolution (p854-ye-200.mov)

Download
41.06 MB

High Resolution (p854-ye-768.mov)

Download
138.01 MB

References

[1]

E. D. Andersen and K. D. Andersen. The MOSEK interior point optimizer for linear programming: an implementation of the homogeneous algorithm. In T. T. H. Frenk, K. Roos and S. Zhang, editors, High Performance Optimization, pages 197--232. Kluwer Academic Publishers, 2000.

[2]

A. Argyriou, R. Hauser, C. Micchelli, and M. Pontil. A DC-programming algorithm for kernel selection. In Proceedings of the International Conference on Machine Learning, pages 41--48, 2006.

Digital Library

[3]

F. R. Bach, G. R. G. Lanckriet, and M. I. Jordan. Multiple kernel learning, conic duality, and the SMO algorithm. In Proceedings of the International Conference on Machine Learning, 2004.

Digital Library

[4]

S. Boyd and L. Vandenberghe. Convex Optimization. Cambridge University Press, 2004.

Digital Library

[5]

N. Cristianini and J. Taylor. An Introduction to Support Vector Machines and other Kernel-based Learning Methods. Cambridge University Press, 2000.

Digital Library

[6]

G. Fung, M. Dundar, J. Bi, and B. Rao. A fast iterative algorithm for Fisher discriminant using heterogeneous kernels. In Proceedings of the International Conference on Machine Learning, 2004.

Digital Library

[7]

G. H. Golub and C. F. Van Loan. Matrix Computations. The Johns Hopkins University Press, third edition, 1996.

[8]

J. J. Hull. A database for handwritten text recognition research. IEEE Trans. Pattern Analysis Machine Intelligence, 16(5):550--554, 1994.

Digital Library

[9]

T. Jebara. Multi-task feature and kernel selection for SVMs. In Proceedings of the International Conference on Machine Learning, 2004. Research Track Paper

Digital Library

[10]

S.-J. Kim, A. Magnani, and S. Boyd. Optimal kernel selection in kernel Fisher discriminant analysis. In Proceedings of the International Conference on Machine Learning, pages 465--472, 2006.

Digital Library

[11]

G. Lanckriet, T. D. Bie, N. Cristianini, M. Jordan, and W. Noble. A statistical framework for genomic data fusion. Bioinformatics, 20(16):2626--2635, 2004.

Digital Library

[12]

G. Lanckriet, N. Cristianini, P. Bartlett, L. E. Ghaoui, and M. I. Jordan. Learning the kernel matrix with semidefinite programming. Journal of Machine Learning Research, 5:27--72, 2004.

Digital Library

[13]

D. Lewis, T. Jebara, and W. S. Noble. Nonstationary kernel combination. In Proceedings of the International Conference on Machine Learning, pages 553--560, 2006.

Digital Library

[14]

M. S. Lobo, L. Vandenberghe, S. Boyd, and H. Lebret. Applications of second-order cone programming. Linear Algebra and its Applications, 284:193-228, 1998.

[15]

S. Mika. Kernel Fisher Discriminants. PhD thesis, University of Technology, Berlin, Oct. 2002.

[16]

S. Mika, G. Rätsch, and K.-R. Müller. A mathematical programming approach to the kernel fisher algorithm. In T. K. Leen, T. G. Dietterich, and V. Tresp, editors, Proceedings of the Annual Conference on Neural Information Processing Systems, pages 591--597. MIT Press, 2001.

[17]

S. Mika, G. Rätsch, J. Weston, B. Schölkopf, and K.-R. Müller. Fisher discriminant analysis with kernels. In Y.-H. Hu, J. Larsen, E. Wilson, and S. Douglas, editors, Neural Networks for Signal Processing IX, pages 41--48. IEEE, 1999.

[18]

Y. Nesterov and A. Nemirovskii. Interior-point polynomial algorithms in convex programming. SIAM Studies in Applied Mathematics. SIAM, 1994.

[19]

D. Newman, S. Hettich, C. Blake, and C. Merz. UCI repository of machine learning databases, 1998.

[20]

J. C. Platt. Fast training of support vector machines using sequential minimal optimization. In Advances in kernel methods: support vector learning, pages 185--208. MIT Press, Cambridge, MA, USA, 1999.

Digital Library

[21]

S. Schölkopf and A. Smola. Learning with Kernels: Support Vector Machines, Regularization, Optimization and Beyond. MIT Press, 2002.

Digital Library

[22]

J. Shawe-Taylor and N. Cristianini. Kernel Methods for Pattern Analysis. Cambridge University Press, 2004.

Digital Library

[23]

S. Sonnenburg, G. Rätsch, C. Schäfer, and B. Schölkopf. Large Scale Multiple Kernel Learning. Journal of Machine Learning Research, 7:1531--1565, July 2006.

Digital Library

[24]

J. F. Sturm. Using SeDuMi 1.02, a MATLAB toolbox for optimization over symmetric cones. Optimization Methods and Software, 11-12:625--653, 1999.

[25]

L. Vandenberghe and S. Boyd. Semidefinite programming. SIAM Review, 38:49--95, 1996.

Digital Library

[26]

V. Vapnik. Statistical learning theory. Wiley, New York, 1998.

Digital Library

[27]

J. Ye. Characterization of a family of algorithms for generalized discriminant analysis on undersampled problems. Journal of Machine Learning Research, 6:483--502, 2005.

Digital Library

[28]

J. Ye, J. Chen, and S. Ji. Discriminant kernel and regularization parameter learning via semidefinite programming. In Proceedings of the International Conference on Machine Learning, 2007.

Digital Library

[29]

J. Ye, J. Chen, Q. Li, and S. Kumar. Classification of drosophila embryonic developmental stage range based on gene expression pattern images. In Proceedings of the Computational Systems Bioinformatics Conference, pages 293--298, 2006.

[30]

A. Zien and C. Ong. Multiclass multiple kernel learning. In Proceedings of the International Conference on Machine Learning, 2007.

Digital Library

Cited By

Basu KSaha AChatterjee S(2017)Large-scale quadratically constrained quadratic program via low-discrepancy sequencesProceedings of the 31st International Conference on Neural Information Processing Systems10.5555/3294771.3294990(2294-2304)Online publication date: 4-Dec-2017
https://dl.acm.org/doi/10.5555/3294771.3294990
Wang JDeng ZJiang YQian PWang S(2014)Multiple-kernel based soft subspace fuzzy clustering2014 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)10.1109/FUZZ-IEEE.2014.6891589(186-193)Online publication date: Jul-2014
https://doi.org/10.1109/FUZZ-IEEE.2014.6891589
Frigui HBchir OBaili N(2013)An Overview of Unsupervised and Semi-Supervised Fuzzy Kernel ClusteringInternational Journal of Fuzzy Logic and Intelligent Systems10.5391/IJFIS.2013.13.4.25413:4(254-268)Online publication date: 30-Dec-2013
https://doi.org/10.5391/IJFIS.2013.13.4.254
Show More Cited By

Index Terms

Learning the kernel matrix in discriminant analysis via quadratically constrained quadratic programming
1. Information systems
  1. Information systems applications
    1. Data mining

Recommendations

Convex relaxations for nonconvex quadratically constrained quadratic programming: matrix cone decomposition and polyhedral approximation

We present a decomposition-approximation method for generating convex relaxations for nonconvex quadratically constrained quadratic programming (QCQP). We first develop a general conic program relaxation for QCQP based on a matrix decomposition scheme ...
On convex relaxations for quadratically constrained quadratic programming

We consider convex relaxations for the problem of minimizing a (possibly nonconvex) quadratic objective subject to linear and (possibly nonconvex) quadratic constraints. Let $$\mathcal{F }$$ denote the feasible region for the linear constraints. We ...
KKT Solution and Conic Relaxation for Solving Quadratically Constrained Quadratic Programming Problems

To find a global optimal solution to the quadratically constrained quadratic programming problem, we explore the relationship between its Lagrangian multipliers and related linear conic programming problems. This study leads to a global optimality ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

KDD '07: Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining

August 2007

1080 pages

ISBN:9781595936097

DOI:10.1145/1281192

General Chair:
Pavel Berkhin
Yahoo!, USA
,
Program Chairs:
Rich Caruana
Cornell University, USA
,
Xindong Wu
University of Vermont, USA

Copyright © 2007 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 12 August 2007

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Article

Conference

KDD07

Sponsor:

KDD07: The 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

August 12 - 15, 2007

California, San Jose, USA

Acceptance Rates

KDD '07 Paper Acceptance Rate 111 of 573 submissions, 19%;

Overall Acceptance Rate 1,133 of 8,635 submissions, 13%

Upcoming Conference

KDD '25

Sponsor:
sigkdd
sigkdd

The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining

August 3 - 7, 2025

Toronto , ON , Canada

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

13
Total Citations
View Citations
723
Total Downloads

Downloads (Last 12 months)12
Downloads (Last 6 weeks)2

Reflects downloads up to 01 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Basu KSaha AChatterjee S(2017)Large-scale quadratically constrained quadratic program via low-discrepancy sequencesProceedings of the 31st International Conference on Neural Information Processing Systems10.5555/3294771.3294990(2294-2304)Online publication date: 4-Dec-2017
https://dl.acm.org/doi/10.5555/3294771.3294990
Wang JDeng ZJiang YQian PWang S(2014)Multiple-kernel based soft subspace fuzzy clustering2014 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)10.1109/FUZZ-IEEE.2014.6891589(186-193)Online publication date: Jul-2014
https://doi.org/10.1109/FUZZ-IEEE.2014.6891589
Frigui HBchir OBaili N(2013)An Overview of Unsupervised and Semi-Supervised Fuzzy Kernel ClusteringInternational Journal of Fuzzy Logic and Intelligent Systems10.5391/IJFIS.2013.13.4.25413:4(254-268)Online publication date: 30-Dec-2013
https://doi.org/10.5391/IJFIS.2013.13.4.254
Baili NFrigui H(2012)Fuzzy clustering with multiple kernels in feature space2012 IEEE International Conference on Fuzzy Systems10.1109/FUZZ-IEEE.2012.6251146(1-8)Online publication date: Jun-2012
https://doi.org/10.1109/FUZZ-IEEE.2012.6251146
Gu QLi ZHan J(2011)Generalized Fisher score for feature selectionProceedings of the Twenty-Seventh Conference on Uncertainty in Artificial Intelligence10.5555/3020548.3020580(266-273)Online publication date: 14-Jul-2011
https://dl.acm.org/doi/10.5555/3020548.3020580
Baili NFrigui H(2011)Relational Fuzzy Clustering with Multiple KernelsProceedings of the 2011 IEEE 11th International Conference on Data Mining Workshops10.1109/ICDMW.2011.145(488-495)Online publication date: 11-Dec-2011
https://dl.acm.org/doi/10.1109/ICDMW.2011.145
Bchir OFrigui H(2011)Fuzzy clustering with Learnable Cluster dependent Kernels2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011)10.1109/FUZZY.2011.6007411(2521-2527)Online publication date: Jun-2011
https://doi.org/10.1109/FUZZY.2011.6007411
Heo GGader P(2011)Robust kernel discriminant analysis using fuzzy membershipsPattern Recognition10.1016/j.patcog.2010.10.00744:3(716-723)Online publication date: 1-Mar-2011
https://dl.acm.org/doi/10.1016/j.patcog.2010.10.007
Mu YZhou B(2011)Non-uniform multiple kernel learning with cluster-based gating functionsNeurocomputing10.1016/j.neucom.2010.11.00174:7(1095-1101)Online publication date: 1-Mar-2011
https://dl.acm.org/doi/10.1016/j.neucom.2010.11.001
Qin HDou DFang Y(2010)Financial Forecasting with Gompertz Multiple Kernel LearningProceedings of the 2010 IEEE International Conference on Data Mining10.1109/ICDM.2010.68(983-988)Online publication date: 13-Dec-2010
https://dl.acm.org/doi/10.1109/ICDM.2010.68
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten