Title :
Asymptotic convergence of an SMO algorithm without any assumptions
Author_Institution :
Dept. of Comput. Sci. & Inf. Eng., Nat. Taiwan Univ., Taipei, Taiwan
fDate :
1/1/2002 12:00:00 AM
Abstract :
The asymptotic convergence of C.-J. Lin (2001) can be applied to a modified SMO (sequential minimal optimization) algorithm by S.S. Keerthi et al. (2001) with some assumptions. The author shows that for this algorithm those assumptions are not necessary
Keywords :
asymptotic stability; convergence; learning automata; minimisation; SVM; assumptions; asymptotic convergence; modified SMO algorithm; sequential minimal optimization algorithm; support vector machine; Analog computers; Circuits; Constraint optimization; Convergence; Delay effects; Differential equations; Helium; Neural networks; Nonlinear equations; Stability;
Journal_Title :
Neural Networks, IEEE Transactions on
