Surrogate Model: A surrogate model, typically a Gaussian Process (GP), is used to approximate the expensive objective function. This model provides both a prediction of the objective function value and an estimate of the uncertainty. Acquisition Function: An acquisition function is used to determine the next point to evaluate. This function balances exploration (sampling where the model uncertainty is high) and exploitation (sampling where the predicted objective function value is high). Common acquisition functions include Expected Improvement (EI) and Probability of Improvement (PI).
