
 Description:
We provide a general solver for squared hinge loss SVM of the form:
min_{w,b} sum_i max(0,y_i(x_i^Tw+b))^2 + Omega(w)
where Omega(w) can be :
 l1 : Omega(w)=sum_i w_i
 l2 : Omega(w)=sum_i w_i^2
 l1l2: Omega(w)=sum_g w_g_2
 l1lp: Omega(w)=sum_g w_g_p
 adaptive l1l2: Omega(w)=sum_g beta_gw_g_2
We also provide a multitask solver where T tasks can be learned simultaneously with joint sparsity constraints (mixed norm regularization).
Note that this toolbox has been designed to be efficient for dense data whereas most of the existing linear svm solvers have been designed for sparse datasets.
 Changes to previous version:
Initial Announcement on mloss.org.
 BibTeX Entry: Download
 Corresponding Paper BibTeX Entry: Download
 Supported Operating Systems: Agnostic
 Data Formats: Any Format Supported By Matlab
 Tags: Large Scale, Kernelmachine, Svm, Bci, Classification, Support Vector Machines, Feature Selection, Linear Svm, Convex Optimization, Gradient Based Learning, Manifold Learning, Optimization, Algorithms, Feature Weighting, Trace Norm, Toolbox, Group Lasso, Lasso, Sparse Learning, Quadratic Programming, Weighting, L1 Regularization, Large Datasets, Regularization, Pattern Recognition, Discriminant Analysis, Linear Model, Generalized Linear Models, Multiclass Support Vector Machine, L1 Minimization, Sparse Representation, L1 Norm, L21 Norm, Dimension Reduction, Multi Task
 Archive: download here
Comments
No one has posted any comments yet. Perhaps you'd like to be the first?
Leave a comment
You must be logged in to post comments.