mloss.org RankSVM NChttp://mloss.orgUpdates and additions to RankSVM NCenThu, 10 Jul 2014 15:51:21 -0000RankSVM NC 1.0http://mloss.org/software/view/557/<html><p>This package is an implementation of a linear RankSVM solver with non-convex regularization. This is the code that has been used for numerical simulation in the paper </p> <p>Laporte, L., Flamary, R., Canu, S., Déjean, S., Mothe, J., "Nonconvex Regularizations for Feature Selection in Ranking With Sparse SVM", Neural Networks and Learning Systems, IEEE Transactions on, Vol. 25, N. 6, pp 1118-1130, 2014. </p> <p>We provide a general solver for squared hinge loss RankSVM with following regularization terms : - l1 norm - lp norm with p&lt;1 - log sum penalty. - MCP </p> <p>This toolbox is in Matlab/Octave and should run on both software. The algorithm used for solving the optimization problem is a Difference of Convex approach as described in here and the algorithm used for solving the sub-problem is a Forward-Backward Splitting algorithm from the FISTA paper. The toolbox also contains code from the paper FSMrank as provided by the authors. </p></html>lea laporte,remi flamaryThu, 10 Jul 2014 15:51:21 -0000http://mloss.org/software/rss/comments/557http://mloss.org/software/view/557/matlabmklclassificationfeature selectionlinear svmconvex optimizationgradient based learningrankingmachine learningoptimizationdata miningsupervised learninglassosparsityregularizationalgorithmdiscriminant analysislinear classifierl1 minimizationl1 normgradient based optimizationnon convex