Global search and Handle function specification
Mostrar comentarios más antiguos
The original code was using "fmincon" to minimize the function MSM_likelihood below:
[parameters,LL,exitflag,output]=fmincon('MSM_likelihood',startingvals,[],[],[],[],LB,UB, [],options,kbar,data,A_template);
HOWEVER, I am trying to run the optimization by using Global Search instead and that requires a function handle, which I believe I used sixmin for that. My code is below:
sixmin = @(input,kbar,data,A_template,estim_flag)MSM_likelihood;
opts = optimoptions(@fmincon,'Algorithm','interior-point');
problem = createOptimProblem('fmincon','x0',startingvals,...
'objective',sixmin(input,kbar,data,A_template,estim_flag),'lb',LB,'ub',UB,...
'options',opts);
gs = GlobalSearch;
[x,f] = run(gs,problem)
Somehow, the code doesn't run as expected. Please help! I really appreciate it!
Respuestas (2)
Walter Roberson
el 26 de Feb. de 2016
0 votos
'objective' needs to be followed by a function handle, but instead you are following it by the result of calling sixmin on particular parameters. You should probably just have sixmin (no parameters following) at that point.
4 comentarios
Tien Nguyen
el 26 de Feb. de 2016
Steven Lord
el 29 de Feb. de 2016
When that function handle is invoked with five input arguments, it will call MSM_likelihood with ZERO input arguments. I'm guessing that's not what you want. If you want to pass all five inputs into MSM_likelihood:
sixmin = @(input,kbar,data,A_template,estim_flag) ...
MSM_likelihood(input,kbar,data,A_template,estim_flag);
I broke this definition across two lines using ... for ease of display in Answers, but you could put it all on one line if you want.
Tien Nguyen
el 2 de Mzo. de 2016
Walter Roberson
el 2 de Mzo. de 2016
sixmin = @(input) MSM_likelihood(input,kbar,data,A_template,estim_flag);
Alan Weiss
el 29 de Feb. de 2016
You might want to try the following line of code instead:
sixmin = @MSM_likelihood;
The function handle for fmincon must contain exactly one argument. See Passing Extra Parameters for more information.
Alan Weiss
MATLAB mathematical toolbox documentation
Categorías
Más información sobre Surrogate Optimization en Centro de ayuda y File Exchange.
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!