Distributed quadratic programming solver for kernel SVM using genetic algorithm

Support vector machine (SVM) is a powerful tool for classification and regression problems, however, its time and space complexities make it unsuitable for large datasets. In this paper, we present GeneticSVM, an evolutionary computing based distributed approach to find optimal solution of quadratic programming (QP) for kernel support vector machine. In Ge-neticSVM, novel encoding method and crossover operation help in obtaining the better solution. In order to train a SVM from large datasets, we distribute the training task over the graphics processing units (GPUs) enabled cluster. It leverages the benefit of the GPUs for large matrix multiplication. The experiments show better performance in terms of classification accuracy as well as computational time on standard datasets like GISETTE, ADULT, etc.

[1]  Kai Wang,et al.  A GPU-Based Parallel Genetic Algorithm for Generating Daily Activity Plans , 2012, IEEE Transactions on Intelligent Transportation Systems.

[2]  B. Freisleben,et al.  Genetic algorithms for binary quadratic programming , 1999 .

[3]  Maozhen Li,et al.  A distributed SVM for image annotation , 2010, 2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery.

[4]  Geoffrey Fox,et al.  Study on Parallel SVM Based on MapReduce , 2012 .

[5]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[6]  Hai Jin,et al.  A distributed SVM method based on the iterative MapReduce , 2015, Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing (IEEE ICSC 2015).

[7]  Asim Munawar,et al.  Advanced genetic algorithm to solve MINLP problems over GPU , 2011, 2011 IEEE Congress of Evolutionary Computation (CEC).

[8]  Thorsten Joachims,et al.  Making large scale SVM learning practical , 1998 .

[9]  Ajalmar R. da Rocha Neto,et al.  Sparse Least Squares Support Vector Machines via Genetic Algorithms , 2013 .

[10]  Le Song,et al.  CA-SVM: Communication-Avoiding Support Vector Machines on Distributed Systems , 2015, 2015 IEEE International Parallel and Distributed Processing Symposium.

[11]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[12]  Kazuhiro Ohkura,et al.  Accelerating steady-state genetic algorithms based on CUDA architecture , 2011, 2011 IEEE Congress of Evolutionary Computation (CEC).

[13]  Asim Munawar,et al.  Optimization of parallel Genetic Algorithms for nVidia GPUs , 2011, 2011 IEEE Congress of Evolutionary Computation (CEC).

[14]  Sergio Herrero-Lopez,et al.  Accelerating SVMs by integrating GPUs into MapReduce clusters , 2011, 2011 IEEE International Conference on Systems, Man, and Cybernetics.

[15]  Ivor W. Tsang,et al.  Core Vector Machines: Fast SVM Training on Very Large Data Sets , 2005, J. Mach. Learn. Res..

[16]  Oscar Herrera,et al.  An Approach to Support Vector Regression with Genetic Algorithms , 2006, 2006 Fifth Mexican International Conference on Artificial Intelligence.

[17]  Tao Huang,et al.  Patent classification system using a new hybrid genetic algorithm support vector machine , 2010, Appl. Soft Comput..

[18]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[19]  Inderjit S. Dhillon,et al.  A Divide-and-Conquer Solver for Kernel Support Vector Machines , 2013, ICML.