[
https://issues.apache.org/jira/browse/MATH-442?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12933083#action_12933083
]
Nikolaus Hansen commented on MATH-442:
--------------------------------------
I think the CMA-ES fits fine into to direct category (but I am familiar with
the meaning of the word direct search, I don't assume everyone is).
Nelder-Mead and CMA-ES are similar in that they do not need derivatives and
they do not even need function values: they are comparison based and only use a
ranking between a number of candidate solutions. Moreover, Nelder-Mead and
CMA-ES share all their invariance properties (not many other optimization
algorithms do). Being rank-based implies invariance under monotonous
transformations of the objective function value, but there are others (e.g.
invariance under coordinate system changes). I believe these are important
properties, also from the application viewpoint. The main conceptional
different to Nelder-Mead: CMA-ES is stochastic (randomized, if you like). The
main practical difference: CMA-ES works also in large dimension and there is a
control parameter for tuning the locality of search.
You could have an elaborate discussion whether CMA-ES estimates a gradient. My
take on it: methods that move opposite to the gradient will regularly fail
anyway.
I also find it strange that algorithms in the general category are in fact less
general.
Where can I subscribe to the list?
> CMA evolution strategy is missing in optimization
> -------------------------------------------------
>
> Key: MATH-442
> URL: https://issues.apache.org/jira/browse/MATH-442
> Project: Commons Math
> Issue Type: New Feature
> Affects Versions: 3.0
> Reporter: Dr. Dietmar Wolz
> Original Estimate: 48h
> Remaining Estimate: 48h
>
> Recently I implemented the optimization algorithm CMA-ES based on
> org.apache.commons.math.linear and used it for the GTOC5 global trajectory
> optimization contest http://gtoc5.math.msu.su/. It implements the
> MultivariateRealOptimizer interface and would nicely fit into the
> org.apache.commons.math.optimization package. The original author of CMA-ES
> (Nikolaus Hansen) volunteered to support me (proof-reading + testing) in the
> creation of a CMA-ES contribution for commons.math.
> The CMA evolution strategy http://www.lri.fr/~hansen/cmaesintro.html is a
> very powerful algorithm for difficult non-linear non-convex optimization
> problems in continuous domain. See http://www.lri.fr/~hansen/cec2005.html for
> a comparison chart. If there is interest I will create a patch including the
> proposed Implementation for evaluation. It seems we would need an additional
> sub-package - org.apache.commons.math.optimization.evolutionary.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
