About: A Matlab implementation of Sparse PCA using the inverse power method for nonlinear eigenproblems. Changes:

About: SALSA (Software lab for Advanced machine Learning with Stochastic Algorithms) is an implementation of the wellknown stochastic algorithms for Machine Learning developed in the highlevel technical computing language Julia. The SALSA software package is designed to address challenges in sparse linear modelling, linear and nonlinear Support Vector Machines applied to large data samples with usercentric and userfriendly emphasis. Changes:Initial Announcement on mloss.org.

About: Scalable learning of global, multitask and local metrics from data Changes:Various minor bug fixes and improvements. The basis and triplet generation now fully supports with datasets with very small classes and arbitrary labels (no need to be consecutive or positive). The computational and memory efficiency of the code when data is high dimensional has been largely improved, and we generate a rectangular (smaller) projection matrix when the number of selected basis is smaller than the dimension. KNN classification with local metrics has been optimized and made significantly less costly in both time and memory.

About: This package is an implementation of a linear RankSVM solver with nonconvex regularization. Changes:Initial Announcement on mloss.org.

About: hapFabia is an R package for identification of very short segments of identity by descent (IBD) characterized by rare variants in large sequencing data. It detects 100 times smaller segments than previous methods. Changes:o citation update o plot function improved

About: A stochastic variant of the mirror descent algorithm employing Langford and Zhang's truncated gradient idea to minimize L1 regularized loss minimization problems for classification and regression. Changes:Fixed major bug in implementation. The components of the iterate where the current example vector is zero were not being updated correctly. Thanks to Jonathan Chang for pointing out the error to us.

About: RLS2 is an instance of multiple kernel learning algorithm to simultaneously learn a regularized predictor and the kernel function. RLS2LIN is a version of RLS2 specialized to linear kernels on each feature. The package contains a set of scripts that implements RLS2 and RLS2LIN, together with a Graphic User Interface to load data, perform training, validation, and plot results. Changes:
