Prequential E-Values for Selected-GP Near-Optimality Certificates
When optimizing an expensive black-box function sequentially, as in hyperparameter optimization, we may want to stop once the best evaluated value is certified within $\varepsilon$ of the global optimum. Such a certificate needs two ingredients: a lower confidence bound for the selected value and an upper confidence en...
A. Tavory, Noa Cohen
· 0 citations