from fminsearch to bayesopt

Question

Barbara Schläpfer 2020-12-15

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/694720-from-fminsearch-to-bayesopt

回答： Alan Weiss 2020-12-15

Hi

I wrote an optimization for material parameters. So far I used the function fminsearch.

[x_min, fval] = fminsearch(@calculate_cost, [5.5e-02, 11.5729, 0.5492], optimset('MaxFunEvals', 100));

I was wondering if there is an simple way to change it to an bayesopt function?

Thanks

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Alan Weiss 2020-12-15

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/694720-from-fminsearch-to-bayesopt#answer_576420

You are free to use bayesopt, but you will have to change your objective function. For bayesopt you first have to create optimizable variables, then write the objective function in terms of those variables. See the workflow here.

I am not sure why you are changing solvers, but there are many solvers available in Optimization Toolbox and Global Optimization Toolbox as well. For help choosing a solver, see Optimization Decision Table and Table for Choosing a Solver.

Alan Weiss

MATLAB mathematical toolbox documentation