Keerthi, S. S.; Shevade, S. K.; Bhattacharyya, C.; Murthy, K. R. K. Improvements to Platt’s SMO algorithm for SVM classifier design. (English) Zbl 1085.68629 Neural Comput. 13, No. 3, 637-649 (2001). Summary: This article points out an important source of inefficiency in Platt’s sequential minimal optimization (SMO) algorithm 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. These modified algorithms perform significantly faster than the original SMO on all benchmark data sets tried. Cited in 68 Documents MSC: 68T05 Learning and adaptive systems in artificial intelligence Software:SVMlight PDF BibTeX XML Cite \textit{S. S. Keerthi} et al., Neural Comput. 13, No. 3, 637--649 (2001; Zbl 1085.68629) Full Text: DOI References: [1] DOI: 10.1080/10556789208805504 This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.