A genetic algorithm would probably be
a pretty good choice for this problem.
It is not in a package, but you can get
the code for the 'genopt' function from
S Poetry on the public domain page of
www.burns-stat.com.
However, I think I understand enough of
the problem to predict that a bespoke
algorithm will be needed. In which case
the introduction to genetic algorithms on
the Tutorials page may be of use.
Patrick Burns
patr...@burns-stat.com
+44 (0)20 8525 0696
http://www.burns-stat.com
(home of "The R Inferno" and "A Guide for the Unwilling S User")
mau...@alice.it wrote:
Thank you.
Unluckily what makes the problem only apparenttly simple (for me) is that we have not differentiable functions and the parameter space is not continuous ... which reduces dramatically the number of choices.
I would be grateful to chat with anyone who has tackled a similar problem.
Maura
-----Messaggio originale-----
Da: David Winsemius [mailto:dwinsem...@comcast.net]
Inviato: dom 26/04/2009 6.55
A: mau...@alice.it
Cc: r-h...@stat.math.ethz.ch
Oggetto: Re: [R] constrained optimization
http://search.r-project.org/cgi-bin/namazu.cgi?query=%22constrained+optimization%22&max=100&result=normal&sort=score&idxname=functions&idxname=Rhelp08
And that is only the help messages from the last two years.'
On Apr 26, 2009, at 12:00 AM, <mau...@alice.it> wrote:
Is there any R package addressing problems of constrained
optimization ?
I have the following "apparently" simple problem:
Given a set V with fixed cardinality: nv
Given a set S whose cardinality is a parameter: nHat
Let the cardinality of the intersection S.and.V be: nHatv
The problem consists of maximizing nHatv/nv subject to a penalty
if nHat > nHatv
It is allowed and even desirable to make set S contain set V
Thank you so much
tutti i telefonini TIM!
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
David Winsemius, MD
Heritage Laboratories
West Hartford, CT
tutti i telefonini TIM!
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
