how to use transformation with fminunc

Dear all,

I am replicating a paper who recommends using fminunc to do a "constrained" optimization through a transformation. I have tried to use directly fmincon (with different algorithms) but the function doesnt optimize, thats the reason I would like to follow the paper advice and use a transformation as follows:

C_bar = lamda*(exp(C)/1+ exp(C))

where lamda is a constant, C is the unconstrained variable and C_bar is the constrained variable. I would really appreciate if you could show me how I could use the transformation in matlab. Do I have to create a seperate function? How can I link it to the optimizer please?

Here is my code

C=[1; 1; 1 ; 1;  1; 1; 1; 1; 1];
options=optimset('Diagnostics','on','Display','iter','TolX',0.001,'TolFun',0.001,'LargeScale','off','HessUpdate','bfgs');
[beta,fval,exitflag,output,grad,hessian] =fminunc(@mll,C,options)

Thanks a lot for your help

Best Regards

SB

[Matt J]

Do you really mean

C_bar = lamda*exp(C)/(1+ exp(C))

[Saad]

Sorry I did miss a parenthese, it is actually

C=lamda* (exp(C)/(1+ exp(C)));

Answer 1

[Matt J]

    Cbar=@(C) lamda*exp(C)/(1+ exp(C));

    fminunc(@(C) mll(Cbar(C)) ,C,options)

[Saad]

thanks for that it is very helpful. It turns out that even with this transformation I do not achieve satisfying results i.e. grad=0; but thank you for your help

S

[Matt J]

Probably because of

'TolX',0.001,'TolFun',0.001

These look like very generous tolerances.

[Saad]

thats true. I will tighten the tolerances a bit and see if it helps the optimizer. Thanks Matt