Learning rates for multi-kernel linear programming classifiers

doi:10.1007/s11464-011-0103-3

Front Math Chin

2011, Vol. 6

Issue (2) : 203-219 https://doi.org/10.1007/s11464-011-0103-3

RESEARCH ARTICLE

Learning rates for multi-kernel linear programming classifiers

Feilong CAO(

), Xing XING

Department of Mathematics, China Jiliang University, Hangzhou 310018, China

Download: PDF(198 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

In this paper, we consider the learning rates of multi-kernel linear programming classifiers. Our analysis shows that the convergence behavior of multi-kernel linear programming classifiers is almost the same as that of multi-kernel quadratic programming. This is implemented by setting a stepping stone between the linear programming and the quadratic programming. An upper bound is presented for general probability distributions and distribution satisfying some Tsybakov noise condition.

Keywords Multi-kernel linear programming learning rate classification

Corresponding Author(s): CAO Feilong,Email:feilongcao@gmail.com

Issue Date: 01 April 2011

Cite this article:

Feilong CAO,Xing XING. Learning rates for multi-kernel linear programming classifiers[J]. Front Math Chin, 2011, 6(2): 203-219.

URL:

https://academic.hep.com.cn/fmc/EN/10.1007/s11464-011-0103-3
https://academic.hep.com.cn/fmc/EN/Y2011/V6/I2/203

1	Anthony M, Bartlett P L. Neural Network Learning: Theoretical Foundations. Cambridge: Cambridge University Press, 1999 doi: 10.1017/CBO9780511624216
2	Aronszajn N. Theory of reproducing kernel. Trans Amer Math Soc , 1950, 68: 337-404
3	Bartleet P L. The sample complexity of pattern classification with neural networks: the size of the wights is more important than the size of the network. IEEE Trans Inform Theory , 1998, 44: 525-536 doi: 10.1109/18.661502
4	Bartleet P L, Jordan M I, Mcaulifle J D. Convexity, classification, and risk bounds. J Amer Stati Assoc , 2006, 101: 138-156 doi: 10.1198/016214505000000907
5	Chen D R, Wu Q, Ying Y, Zhou D X. Support vector machine soft margin classifier: error analysis. J Machine Learning Research , 2004, 5: 1143-1175
6	Cucker F, Smale S. On the mathematical foundations of learning. Bull Amer Math Soc , 2001, 39: 1-49 doi: 10.1090/S0273-0979-01-00923-5
7	Devroye L, Gy?rfi L, Lugosi G. A Probabilistic Theory of Pattern Recognition. Berlin: Springer-Verlag, 1997
8	Lugosi G, Vayatis N. On the Bayes-risk consistency of regularized boosting methods. Ann Statist , 2004, 32: 30-55
9	Pollsard D. Convergence of Stochastic Processes. Berlin: Springer-Verlag, 1984
10	Scovel C, Steinwart I. Fast Rates for Support Vector Machines. Berlin/Heidelberg: Springer-Verlag, 2005
11	Smale S, Zhou D X. Shannon sampling and function reconstruction from point values. Bull Amer Math Soc , 2004, 41: 279-305 doi: 10.1090/S0273-0979-04-01025-0
12	Tsybakov A B. Optimal aggregation of classifiers in statistical learning. Ann Statis , 2004, 32: 135-166 doi: 10.1214/aos/1079120131
13	Vapnik V. Statistical Learning Theory. New York: John Wiley & Sons, 1998
14	Wahba G. Spline Models for Observational Data. Philadelphia: SIAM, 1990
15	Wu Q, Ying Y, Zhou D X. Multi-kernel regularized classifiers. J Complexity , 2007, 23: 108-134 doi: 10.1016/j.jco.2006.06.007
16	Wu Q, Zhou D X. SVM soft margin classifiers: linear programming versus quadratic programming. Neural Computation , 2005, 17: 1160-1187 doi: 10.1162/0899766053491896
17	Zhang T. Covering number bounds of certain regularized linear function classes. J Machine Learning Research , 2002, 2: 527-550 doi: 10.1162/153244302760200713
18	Zhang T. Statistical behavior and consistency of classification methods based on convex risk minimization. Ann Stat , 2004, 32: 56-85 doi: 10.1214/aos/1079120130

[1]	Yu LI, Guiyun CHEN. Normalized integral table algebras generated by a faithful real element of degree 2 and having 4 linear elements[J]. Front. Math. China, 2019, 14(6): 1231-1258.
[2]	Jiajie HUA, Xiaochun FANG, Xiao-Ming XU. Continuity of functors with respect to generalized inductive limits[J]. Front. Math. China, 2019, 14(3): 551-566.
[3]	Li-meng XIA,Naihong HU. A class of Lie algebras arising from intersection matrices[J]. Front. Math. China, 2015, 10(1): 185-198.
[4]	Jixia YUAN, Wende LIU. Filtration, automorphisms, and classification of infinite-dimensional odd contact superalgebras[J]. Front Math Chin, 2013, 8(1): 203-216.
[5]	Ruipu BAI, Guojie SONG, Yaozhong ZHANG. On classification of n-Lie algebras[J]. Front Math Chin, 2011, 6(4): 581-606.
[6]	Chuankuan YUAN. Ky Fan (1914-2010), he spent every waking moment thinking about mathematics[J]. Front Math Chin, 2011, 6(3): 379-390.
[7]	Qinhui JIANG, Changguo SHAO. Finite groups with 24 elements of maximal order[J]. Front Math Chin, 2010, 5(4): 665-678.
[8]	LI Min, HE Bingsheng. Prediction-correction alternating direction method for a class of constrained min-max problems[J]. Front. Math. China, 2007, 2(1): 103-121.

Viewed

Full text

Abstract

Cited

Shared

Discussed