A fast dual algorithm for kernel logistic regression

被引：67
作者：
Keerthi, SS
Duan, KB
Shevade, SK
Poo, AN
机构：
[1] Yahoo Res Labs, Pasadena, CA 91105 USA
[2] Natl Univ Singapore, Dept Mech Engn, Control Div, Singapore, Singapore
[3] Indian Inst Sci, Dept Comp Sci & Automat, Bangalore 560012, Karnataka, India
来源：
MACHINE LEARNING | 2005年 / 61卷 / 1-3期
关键词：
classification; logistic regression; kernel methods; SMO algorithm;
D O I：
10.1007/s10994-005-0768-5
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This paper gives a new iterative algorithm for kernel logistic regression. It is based on the solution of a dual problem using ideas similar to those of the Sequential Minimal Optimization algorithm for Support Vector Machines. Asymptotic convergence of the algorithm is proved. Computational experiments show that the algorithm is robust and fast. The algorithmic ideas can also be used to give a fast dual algorithm for solving the optimization problem arising in the inner loop of Gaussian Process classifiers.
引用
收藏
页码：151 / 165
页数：15
相关论文
共 13 条
[1]  
[Anonymous], 1998, UCI REPOSITORY MACHI
[2]  
[Anonymous], ADV LARGE MARGIN CLA
[3]  
BAILEY RR, 1993, P SPIE, V1944
[4]  
CAUWENBERGHS G, 2001, ISCAS
[5]  
JAAKKOLA TS, 1999, P 7 INT WORKSH ART I
[6]   Improvements to Platt's SMO algorithm for SVM classifier design [J].
Keerthi, SS ;
Shevade, SK ;
Bhattacharyya, C ;
Murthy, KRK .
NEURAL COMPUTATION, 2001, 13 (03) :637-649
[7]  
Platt J., 1998, MICROSOFT RES
[8]  
RATSCH G, 1999, BENCHMARK DATASETS
[9]  
Roth V., 2001, Pattern Recognition. 23rd DAGM Symposium. Proceedings (Lecture Notes in Computer Science Vol.2191), P246
[10]  
Vapnik V, 1999, NATURE STAT LEARNING
12