L. Zhukov

Modernizing HEBO: a robust Bayesian optimization baseline for practical heteroskedastic and non-stationary problems

This work introduces tidyHEBO, a robust Bayesian optimization model inspired by heteroskedastic evolutionary Bayesian optimization (HEBO) for single-objective, sequential optimization, and reconstructs the HEBO design philosophy in BoTorch and revises surrogate training, output-warping selection, acquisition function e...