Algorithm 1: Bayesian Optimization Hyperparameter Framework

$\begin{array}{l}Input: The number ofparameters n_0, The maximum number of iterations \mathrm{T},\\ The search space for parameters X, The function for evaluate model f,\\ Surrogate models M, Acquisition Function S\end{array}$

$Output: The optimal parameter combination x$

$D\leftarrow InitSamples(f,X)$

$For i\leftarrow {\left|D\right|}_{}to T_{} do:$

$\hspace{1em}\hspace{1em}p\left(y|x,D\right)\leftarrow FitModel(M,D)$

$\hspace{1em}\hspace{1em}{x}_i\leftarrow \underset{x\in X}{\arg \max }S\left(x,p\left(y|x,D\right)\right)$

$\hspace{1em}\hspace{1em}{y}_i\leftarrow f(x_i)$

$\hspace{1em}\hspace{1em}D\leftarrow D\cup \left(x_i,y_i\right)$

$end for$