Hyper Parameter Tuning for Machine Learning, Using Bayesian Optimization (MlBayesOpt)
Hyper parameter tuning using Bayesian optimization (Shahriari et al. <doi:10.1109/JPROC.2015.2494218>) for support vector machine, random forest, and extreme gradient boosting (Chen & Guestrin (2016) <doi:10.1145/2939672.2939785>). Unlike already existing packages (e.g. ‘mlr’, ‘rBayesianOptimization’, or ‘xgboost’), there is no need to change in accordance with the package or method of machine learning. You just prepare a data frame with feature vectors and the label column that has any class (‘character’, ‘factor’, ‘integer’). Moreover, to write a optimization function, you have only to specify the data and the column name of the label to classify.

Interface to the ‘HDF5’ Binary Data Format (hdf5r)
HDF5′ is a data model, library and file format for storing and managing large amounts of data. This package provides a nearly feature complete, object oriented wrapper for the ‘HDF5’ API <https://…/RM_H5Front.html> using R6 classes. Additionally, functionality is added so that ‘HDF5’ objects behave very similar to their corresponding R counterparts.

Algorithms using Alternating Direction Method of Multipliers (ADMM)
Provides algorithms to solve popular optimization problems in statistics such as regression or denoising based on Alternating Direction Method of Multipliers (ADMM). See Boyd et al (2010) <doi:10.1561/2200000016> for complete introduction to the method.