General partition search algorithm (local search, genetic algorithm, ...)

classic Classic list List threaded Threaded
2 messages Options
Reply | Threaded
Open this post in threaded view
|

General partition search algorithm (local search, genetic algorithm, ...)

Aleš Žiberna-3
Dear R users!

I was wondering if there exists (in R) any general algorithm for finding
optimal partition (optimal allocation of n units into k groups or bins),
such as local search, genetic algorithm, tabu search, ...

By general I mean such that would find an (approximately) optimal partition
based on some user specified criterion function, that would be evaluated on
the data and partition.

It is especially essential that the algorithm does not require any unit
fitness values, only the value of criterion function (or fitness) for the
partition as a whole.

Thanks for any replies!

Best regards,
Ales Ziberna

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Reply | Threaded
Open this post in threaded view
|

Re: General partition search algorithm (local search, genetic algorithm, ...)

Gabor Grothendieck
You may be able to use linear programming.  Check out this thread:

   http://tolstoy.newcastle.edu.au/~rking/R/help/05/11/16009.html

On 1/16/06, Aleš Žiberna <[hidden email]> wrote:

> Dear R users!
>
> I was wondering if there exists (in R) any general algorithm for finding
> optimal partition (optimal allocation of n units into k groups or bins),
> such as local search, genetic algorithm, tabu search, ...
>
> By general I mean such that would find an (approximately) optimal partition
> based on some user specified criterion function, that would be evaluated on
> the data and partition.
>
> It is especially essential that the algorithm does not require any unit
> fitness values, only the value of criterion function (or fitness) for the
> partition as a whole.
>
> Thanks for any replies!
>
> Best regards,
> Ales Ziberna
>
> ______________________________________________
> [hidden email] mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
>

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html