|
From: | Steven G. Johnson |
Subject: | [Help-gsl] Re: [Rd] Optimization in R - NLopt library |
Date: | Wed, 18 Nov 2009 21:59:49 -0500 |
User-agent: | Thunderbird 2.0.0.23 (Macintosh/20090812) |
Andrew Clausen wrote:
I've been working on improving R's optim() command, which does general purpose unconstrained optimization. Obviously, this is important for many statistics computations, such as maximum likelihood, method of moments, etc. I have focused my efforts of the BFGS method, mainly because it best matches my current projects.
Hi, I came across this posting from a couple of years ago. If you are still working on this, you might be interested in my free-software (LGPL) library NLopt, which provides a single API for a large number of nonlinear-optimization routines:
http://ab-initio.mit.edu/nlopt It includes:* Unconstrained optimization, bound constraints, and general nonlinear inequality constraints
* Global and local optimization* Optimization using function values only and optimization that exploits gradient information if it is available.
Currently, it is callable from C, Fortran, Matlab, and GNU Octave, but it would be great to have a GNU R interface as well.
Regards, Steven G. Johnson
[Prev in Thread] | Current Thread | [Next in Thread] |