HEBO: Heteroscedastic Evolutionary Bayesian Optimisation
We introduce HEBO: Heteroscedastic Evolutionary Bayesian Optimisation that won the NeurIPS 2020 black-box optimisation competition. We present non-conventional modifications to the surrogate model and acquisition maximisation process and show such a combination superior against all baselines provided by the Bayesmark package. Lastly, we perform an ablation study to highlight the components that contributed to the success of HEBO.
READ FULL TEXT