When NLP is used to estimate parameters of a statistical model(using least
squares, max Chi-sq or Max likelihood), goodness-of-fit and estimation errors 
are
derived from the inverse of the matrix of second derivatives (Hessian) at the
solution point.

Many algorithms produce an estimate of the Hessian as part of their progress, 
and
in other cases it is possible to estimate the matrix in a way similar to
estimating the gradient when analytic derivatives are not available.

It would be useful to add a function to the nlopt library to extract the Hessian
(or its inverse) at the solution.

Thanks,

Zvi Tarem


_______________________________________________
NLopt-discuss mailing list
[email protected]
http://ab-initio.mit.edu/cgi-bin/mailman/listinfo/nlopt-discuss

Reply via email to