Support vector machine classifiers for large data sets.

Gertz, E. M. ; Griffin, J. D.

Argonne National Laboratory

关键词: Pattern Recognition;    Classification;    Computer Codes;    Learning;    99 General And Miscellaneous//Mathematics, Computing, And Information Science;   

DOI  :  10.2172/881587
RP-ID  :  ANL/MCS-TM-289
RP-ID  :  W-31-109-ENG-38
RP-ID  :  881587

美国|其它

来源: UNT Digital Library

【 摘 要 】

This report concerns the generation of support vector machine classifiers for solving the pattern recognition problem in machine learning. Several methods are proposed based on interior point methods for convex quadratic programming. Software implementations are developed by adapting the object-oriented packaging OOQP to the problem structure and by using the software package PETSc to perform time-intensive computations in a distributed setting. Linear systems arising from classification problems with moderately large numbers of features are solved by using two techniques--one a parallel direct solver, the other a Krylov-subspace method incorporating novel preconditioning strategies. Numerical results are provided, and computational experience is discussed.