Package: sparseLM 0.5

sparseLM: Interface to the 'sparseLM' Levenberg-Marquardt Library

Provides an R interface to the 'sparseLM' C library for large-scale nonlinear least squares problems with arbitrarily sparse Jacobians. The underlying solver implements a sparse variant of the Levenberg-Marquardt algorithm for minimizing sum-of-squares objective functions, supports user-supplied analytic Jacobians or finite-difference approximation, and is designed to exploit sparsity for improved memory use and performance. This package exposes the solver in R and uses sparse matrix classes and the 'CHOLMOD' sparse Cholesky factorization routines through the 'Matrix' package interface. Methods from the C library are described in Lourakis (2010) <doi:10.1007/978-3-642-15552-9_4>.

Authors:Colin Smith [aut, cre], Manolis Lourakis [aut]