Welcome, Guest. Please Login
YaBB - Yet another Bulletin Board
 
  HomeHelpSearchLogin  
 
optimisation questions (Read 3425 times)
konrad
Junior Member
**
Offline


I love YaBB 1G - SP1!

Posts: 53
optimisation questions
Nov 3rd, 2005 at 5:46am
 
Hi Sergei,

On optimising models using Yang's M1a (neutral) and M2a (selection) omega distributions, I frequently get higher likelihoods for the constrained model. This seems to point to an optimisation problem, which is perhaps not very surprising as I am using an unusually large number of parameters (my model is probably overparameterised). The problem does not appear with more usual models.

How can I play around with the optimisation criteria? For instance, is there a likelihood threshold that determines at which point the optimisation stops? Also, is the algorithm completely deterministic or is it worth running it more than once to see if it always converges to the same answer?

regards
Konrad
Back to top
 
WWW WWW  
IP Logged
 
Sergei
YaBB Administrator
*****
Offline


Datamonkeys are forever...

Posts: 1658
UCSD
Gender: male
Re: optimisation questions
Reply #1 - Nov 3rd, 2005 at 7:56am
 
Dear Konrad,

[quote author=konrad  link=1131025616/0#0 date=1131025616]

On optimising models using Yang's M1a (neutral) and M2a (selection) omega distributions, I frequently get higher likelihoods for the constrained model. This seems to point to an optimisation problem, which is perhaps not very surprising as I am using an unusually large number of parameters (my model is probably overparameterised). The problem does not appear with more usual models.
[/quote]

This seems odd. There should not be inordinately many parameters in these two models; perhaps some parameters are being declared as local, inadvertently? You should try to list all model parameters (e.g. using the -p command line option and choosing View Likelihood -> Show Parameter list at the end of the run if using a command line version; or using the Object Inspector for the appropriate likelihood function to bring up the parameter table in the GUI) and see if any of them are extraneous.

[quote]
How can I play around with the optimisation criteria? For instance, is there a likelihood threshold that determines at which point the optimisation stops? Also, is the algorithm completely deterministic or is it worth running it more than once to see if it always converges to the same answer?
[/quote]

Default optimization algorithm is determinstic (given a starting point).
Some of the HyPhy constants which control optimization options are listed below. The meaning can be looked up in http://www.hyphy.org/pubs/Commands.pdf

OPTIMIZATION_METHOD
OPTIMIZATION_PRECISION
GLOBAL_STARTING_POINT
USE_DISTANCES
MAXIMUM_ITERATIONS_PER_VARIABLE
USE_LAST_RESULTS
RANDOM_STARTING_PERTURBATIONS

HTH,
Sergei
Back to top
 

Associate Professor
Division of Infectious Diseases
Division of Biomedical Informatics
School of Medicine
University of California San Diego
WWW WWW  
IP Logged
 
konrad
Junior Member
**
Offline


I love YaBB 1G - SP1!

Posts: 53
Re: optimisation questions
Reply #2 - Nov 3rd, 2005 at 8:11am
 
Thanks for the optimisation info. Regarding parameters, I guess I was unclear: what I am doing is to untie topologies over many (20) partitions, so the program has to optimise a large number of branch length parameters. The problem does not appear when I use a single partition, so I suspect it is the simultaneous optimisation of many branch lengths along with the omega distribution parameters that is causing it to go astray.

Konrad
Back to top
 
WWW WWW  
IP Logged
 
konrad
Junior Member
**
Offline


I love YaBB 1G - SP1!

Posts: 53
Re: optimisation questions
Reply #3 - Nov 4th, 2005 at 6:25am
 
Looks like I was right: using a tighter OPTIMIZATION_PRECISION makes the problem go away in most cases. Using 5 test cases, with the default value of OPTIMIZATION_PRECISION the unconstrained model had lower lnL in 4 of them; tightening the precision by a factor 100 removes the problem for 3 of the 4 (the remaining one ran for ages and still gave a lower lnL).

Konrad
Back to top
 
WWW WWW  
IP Logged
 
avilella
YaBB Newbies
*
Offline


I love YaBB 1G - SP1!

Posts: 35
Re: optimisation questions
Reply #4 - Nov 4th, 2005 at 7:20am
 
I have followed this thread with great interest and the latest reply
is quite informative. I was also a little worried with some
differences in the results I was obtaining with HYPHY vs PAML.

It would be fantastic if you could post this tests cases you used
somewhere so that this could be given as a proof case scenario.

Thanks in advance,

    Albert.
Back to top
 
 
IP Logged
 
Sergei
YaBB Administrator
*****
Offline


Datamonkeys are forever...

Posts: 1658
UCSD
Gender: male
Re: optimisation questions
Reply #5 - Nov 4th, 2005 at 7:58am
 
Dear Konrad and Albert,

One more thing: check MAXIMUM_ITERATIONS_PER_VARIABLE and messages.log for messages to the effect "Optimization routines returned before precision achieved...".

Finally, the functions which converge poorly are usually indicative of flat likelihood surfaces (e.g. overparameterized models), or strange domain artefacts (which usually arise in mixture and constraint problems).

Cheers,
Sergei
Back to top
 

Associate Professor
Division of Infectious Diseases
Division of Biomedical Informatics
School of Medicine
University of California San Diego
WWW WWW  
IP Logged