Nested sequential minimal optimization for support vector machines

Authors:
Alessandro Ghio;Davide Anguita;Luca Oneto;Sandro Ridella;Carlotta Schatten
Affiliations:
DITEN, University of Genova, Genova, Italy;DITEN, University of Genova, Genova, Italy;DITEN, University of Genova, Genova, Italy;DITEN, University of Genova, Genova, Italy;DITEN, University of Genova, Genova, Italy
Venue:
ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part II
Year:
2012

Citing 9
Cited 0

Using analytic QP and sparseness to speed training of support vector machines

Proceedings of the 1998 conference on Advances in neural information processing systems II
Improvements to Platt's SMO Algorithm for SVM Classifier Design

Neural Computation
An Experimental Study on Pedestrian Classification

IEEE Transactions on Pattern Analysis and Machine Intelligence
Working Set Selection Using Second Order Information for Training Support Vector Machines

The Journal of Machine Learning Research
An empirical evaluation of deep architectures on problems with many factors of variation

Proceedings of the 24th international conference on Machine learning
LIBLINEAR: A Library for Large Linear Classification

The Journal of Machine Learning Research
LIBSVM: A library for support vector machines

ACM Transactions on Intelligent Systems and Technology (TIST)
Three-parameter sequential minimal optimization for support vector machines

Neurocomputing
A review of optimization methodologies in support vector machines

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose in this work a nested version of the well–known Sequential Minimal Optimization (SMO) algorithm, able to contemplate working sets of larger cardinality for solving Support Vector Machine (SVM) learning problems. Contrary to several other proposals in literature, neither new procedures nor numerical QP optimizations must be implemented, since our proposal exploits the conventional SMO method in its core. Preliminary tests on benchmarking datasets allow to demonstrate the effectiveness of the presented method.