I am given a dataset $\mathcal{D} = \{\mathbf{x}_i\}_{i=1}^n$ and I need to find the point (in my case a material) $\mathbf{x}^*$ that maximizes a property $y$ (which can be obtained from a black-box function $f(\mathbf{x}$), performing the least amount of labeling (because it is expensive).
I have checked Bayesian optimization but it uses a Gaussian process as a surrogate model which makes the training extremely slow for a high-dimensional feature space and large datasets (high $n$).
Are there any alternatives to Bayesian optimization for such a task?
I have checked Particle Swarm optimization but I think it is not applicable to my case, since the particles must be allowed to access any $\mathbf{x}$ while $\mathcal{D}$ contains only specific points.
I should add that the features of $\mathcal{D}$ are all continuous.
