Genetic Algorithms

Flexible general-purpose toolbox implementing genetic algorithms (GAs) for stochastic optimisation. Binary, real-valued, and permutation representations are available to optimize a fitness function, i.e. a function provided by users depending on their objective function. Several genetic operators are available and can be combined to explore the best settings for the current task. Furthermore, users can define new genetic operators and easily evaluate their performances. Local search using general-purpose optimisation algorithms can be applied stochastically to exploit interesting regions. GAs can be run sequentially or in parallel, using an explicit master-slave parallelisation or a coarse-grain islands approach. For more details see Scrucca (2013) and Scrucca (2017) .

A Replacement and Extension of the 'optim' Function

Provides a test of replacement and extension of the optim() function to unify and streamline optimization capabilities in R for smooth, possibly box constrained functions of several or many parameters. This version has a reduced set of methods and is intended to be on CRAN.

Optimal, Fast, and Reproducible Univariate Clustering

Fast, optimal, and reproducible weighted univariate clustering by dynamic programming. Four problems are solved, including univariate k-means (Wang & Song 2011) (Song & Zhong 2020) , k-median, k-segments, and multi-channel weighted k-means. Dynamic programming is used to minimize the sum of (weighted) within-cluster distances using respective metrics. Its advantage over heuristic clustering in efficiency and accuracy is pronounced when there are many clusters. Multi-channel weighted k-means groups multiple univariate signals into k clusters. An auxiliary function generates histograms adaptive to patterns in data. This package provides a powerful set of tools for univariate data analysis with guaranteed optimality, efficiency, and reproducibility, useful for peak calling on temporal, spatial, and spectral data.

Limited Memory BFGS Minimizer with Bounds on Parameters with optim() 'C' Interface

Interfacing to Nocedal et al. L-BFGS-B.3.0 (See < http://users.iems.northwestern.edu/~nocedal/lbfgsb.html>) limited memory BFGS minimizer with bounds on parameters. This is a fork of 'lbfgsb3'. This registers a 'R' compatible 'C' interface to L-BFGS-B.3.0 that uses the same function types and optimization as the optim() function (see writing 'R' extensions and source for details). This package also adds more stopping criteria as well as allowing the adjustment of more tolerances.

Multiple Criteria Optimization Algorithms and Related Functions

A collection of function to solve multiple criteria optimization problems using genetic algorithms (NSGA-II). Also included is a collection of test functions.

General Purpose Optimization in R using C++

Perform general purpose optimization in R using C++. A unified wrapper interface is provided to call C functions of the five optimization algorithms ('Nelder-Mead', 'BFGS', 'CG', 'L-BFGS-B' and 'SANN') underlying optim().

Active Set and Generalized PAVA for Isotone Optimization

Contains two main functions: one for solving general isotone regression problems using the pool-adjacent-violators algorithm (PAVA); another one provides a framework for active set methods for isotone optimization problems with arbitrary order restrictions. Various types of loss functions are prespecified.

Approximate Optimal Transport Between Two-Dimensional Grids

Can be used for optimal transport between two-dimensional grids with respect to separable cost functions of l^p form. It utilizes the Frank-Wolfe algorithm to approximate so-called pivot measures: One-dimensional transport plans that fully describe the full transport, see G. Auricchio (2023) . For these, it offers methods for visualization and to extract the corresponding transport plans and costs. Additionally, related functions for one-dimensional optimal transport are available.

Model and Solve Mixed Integer Linear Programs

Model mixed integer linear programs in an algebraic way directly in R. The model is solver-independent and thus offers the possibility to solve a model with different solvers. It currently only supports linear constraints and objective functions. See the 'ompr' website < https://dirkschumacher.github.io/ompr/> for more information, documentation and examples.

Functions for Optimal Matching

Distance based bipartite matching using minimum cost flow, oriented to matching of treatment and control groups in observational studies ('Hansen' and 'Klopfer' 2006 ). Routines are provided to generate distances from generalised linear models (propensity score matching), formulas giving variables on which to limit matched distances, stratified or exact matching directives, or calipers, alone or in combination.