(November Series #4) Long-run Behaviour of Multi-fidelity Bayesian Optimisation

Gbetondji Dovonon will discuss our recent NeurIPS workshop paper on "Long-run Behaviour of Multi-fidelity Bayesian Optimisation".

Time: Nov 28th, 2023 at 2:00 PM (London Time) [online]

Link: https://us06web.zoom.us/j/87380098143

Abstract: Multi-fidelity Bayesian Optimisation (MFBO) has been shown to generally converge faster than single-fidelity Bayesian Optimisation (SFBO). Inspired by recent benchmark papers, we are investigating the long-run behaviour of MFBO, based on observations in the literature that it might under-perform in certain scenarios. An under-performance of MBFO in the long-run could significantly undermine its application to many research tasks, especially when we are not able to identify when the under-performance begins. We create a simple benchmark study, showcase empirical results and discuss scenarios, concluding with inconclusive results.