[mlpack] GSoC 2014 simulated annealing optimizer

Zhihao Lou lzh1984 at gmail.com
Tue Jul 8 10:50:23 EDT 2014


Hi Ryan,




On Tue, Jul 8, 2014 at 7:51 AM, Ryan Curtin <gth671b at mail.gatech.edu> wrote:
>
> Ok; I have added your name to core.hpp and also on the website:
> http://www.mlpack.org/about.html


Thank you for adding me to the contributor's list!


> I think letting the function define its bounds is probably the best way
> to approach the problem.  Otherwise, we would have to modify the
> existing optimizers to deal with the search boundaries.  So it is
> probably simpler to allow the user to define a bounded function by
> something like
>
> double Evaluate(const arma::mat& coordinates)
> {
>   if (OutsideBoundaries(coordinates))
>     return DBL_MAX;
>   else
>     return ActuallyEvaluate(coordinates);
> }
>
> Do you think that's reasonable?  If you have a better solution, let me
> know, but I think that's the best way to go for now.
>

I agree with your idea. This also means there's no need to change the
annealer code for bounded search space.:)

Best regards,

Zhihao Lou
PhD Candidate
Department of Computer Science
The University of Chicago
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack/attachments/20140708/f308f719/attachment.html>


More information about the mlpack mailing list