Asymptotic convergence of an SMO algorithm without any assumptions

Chih-Jen Lin

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.
BibTeX
@article{lin2002asymptotic,
  author = {Chih-Jen Lin},
  title = {{Asymptotic convergence of an SMO algorithm without any assumptions}},
  journal = {IEEE Trans. Neural Networks},
  year = {2002},
  doi = {10.1109/72.977319},
}

Loading related content...

Figure