commons-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Frank Hess (JIRA)" <j...@apache.org>
Subject [jira] [Updated] (MATH-864) CMAESOptimizer does not enforce bounds
Date Wed, 19 Sep 2012 22:09:07 GMT

     [ https://issues.apache.org/jira/browse/MATH-864?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

Frank Hess updated MATH-864:
----------------------------

    Attachment: Math864Test.java

Test program that shows bug.
                
> CMAESOptimizer does not enforce bounds
> --------------------------------------
>
>                 Key: MATH-864
>                 URL: https://issues.apache.org/jira/browse/MATH-864
>             Project: Commons Math
>          Issue Type: Bug
>    Affects Versions: 3.0, 3.1
>            Reporter: Frank Hess
>         Attachments: Math864Test.java
>
>
> The CMAESOptimizer can exceed the bounds passed to optimize.  Looking at the generationLoop
in doOptimize(), it does a bounds check by calling isFeasible() but if checkFeasableCount
is zero (the default) then isFeasible() is never even called.  Also, even with non-zero checkFeasableCount
it may give up before finding an in-bounds offspring and go forward with an out-of-bounds
offspring.  This is against svn revision 1387637.  I can provide an example program where
the optimizer ends up with a fit outside the prescribed bounds if that would help.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira

Mime
View raw message