Abstract

This paper points out an important source of confusion and inefficiency in Smola and Scholkopf's Sequential Minimal Optimization (SMO) algorithm for SVM regression that is caused by the use of a single threshold value. Using clues from the KKT conditions for the dual problem, two threshold parameters are employed to derive modifications of SMO for regression. These modified algorithms perform significantly faster than the original SMO on the datasets tried. 1 Introduction Support Vector...

Description

citeulike

Links and resources

Tags

community

  • @kdubiq
  • @a_olympia
  • @dblp
@a_olympia's tags highlighted