AI RESEARCH
Provable Accelerated Bayesian Optimization with Knowledge Transfer
arXiv CS.LG
•
ArXi:2511.03125v2 Announce Type: replace-cross We study how to accelerate Bayesian optimization (BO) on a target task by transferring historical knowledge from related source tasks. Existing work on BO with knowledge transfer either lacks theoretical guarantees or achieves the same regret as BO in the non-transfer setting, $\widetilde{O}(\sqrt{T \gamma_f})$, where $T$ is the number of evaluations of the target function and $\gamma_f$ denotes its information gain.