Agreed on the default algorithm issue. That is important for users to
know, and I'm happy to underline it. Also that CG (which is based on one
of my codes) should be deprecated. BFGS (also based on one of my codes
from long ago) does much better than I would ever have expected.
Over the years
and just to add to john's comments, since he's too modest, in my
experience, the algorithm in the rvmmin package ( written by john ) shows
great improvement compared to the L-BFGS-B algorithm so I don't use
L-BFGS-B anymore. L-BFGS-B often has a dangerous convergence issue in
that it can
Not contradicting Ravi's message, but I wouldn't say Nelder-Mead is
"bad" per se. It's issues are that it assumes the parameters are all on
the same scale, and the termination (not convergence) test can't use
gradients, so it tends to get "near" the optimum very quickly -- say
only 10% of the
Hi,
While I agree with the comments about paying attention to parameter scaling, a
major issue here is that the default optimization algorithm, Nelder-Mead, is
not very good. It is unfortunate that the optim implementation chose this as
the "default" algorithm. I have several instances
In econometrics it was common to start an optimization with Nelder-Mead and
then switch to one of the other algorithms to finish the optimization. As
John Nash states NM gets one close. switching then speeds the final
solution.
John
John C Frain
3 Aranleigh Park
Rathfarnham
Dublin 14
Ireland
Thanks a lot, Ravi.
Indeed you best understood the point of my email.
I am perfectly aware that most of the optimization algorithms find
local rather than global minima and therefore the choice of the
initial parameters plays (at least in principle) a role.
Nevertheless, my optimization problem
Hi John,
My main point is not about Nelder-Mead per se. It is *primarily* about the
Nelder-Mead implementation in optim().
The users of optim() should be cautioned regarding the default algorithm and
that they should consider alternatives such as "BFGS" in optim(), or other
implementations
7 matches
Mail list logo