Parallel cost-aware optimization of multidimensional black-box functions
O. Sihlovec (TU Delft - Electrical Engineering, Mathematics and Computer Science)
Matthijs T. J. Spaan – Mentor (TU Delft - Algorithmics)
J.A. de Vries – Mentor (TU Delft - Algorithmics)
C. Lofi – Graduation committee member (TU Delft - Web Information Systems)
More Info
expand_more
This link redirects to the student's code repository containing the code, which has been utilized throughout the research and which can be used to reproduce the results outlined in the paper.
https://github.com/osihlovec/ca-qeiOther than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Scientific problems are often concerned with optimization of control variables of complex systems, for instance hyperparameters of machine learning models. A popular solution for such intractable environments is Bayesian optimization. However, many implementations disregard dynamic evaluation costs associated with the optimization procedure. Furthermore, another common trope among
Bayesian algorithms is that they are short-sighted and do not consider long-term effects of their actions. This paper investigates the viability of multitimestep cost-aware Bayesian optimizers and evaluates their performance in environments with delayed rewards. To this end, we combine existing works on parallel Bayesian optimizers and costaware heuristics. Our findings reveal that although
such parallel optimizers yield more optimal results and are more resistant to delayed feedback compared to their myopic counterparts, they are unable to achieve cost-awareness.