BOO achieves exponentially decaying regret O(N^{-√N}) by combining Bayesian optimisation and partitioning-based optimistic optimisation for Matérn GP functions with ν > 4 + D/2.
Bayesian Optimization with Exponential Convergence
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This paper presents a Bayesian optimization method with exponential convergence without the need of auxiliary optimization and without the delta-cover sampling. Most Bayesian optimization methods require auxiliary optimization: an additional non-convex global optimization problem, which can be time-consuming and hard to implement in practice. Also, the existing Bayesian optimization method with exponential convergence requires access to the delta-cover sampling, which was considered to be impractical. Our approach eliminates both requirements and achieves an exponential convergence rate.
fields
cs.LG 1years
2021 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Bayesian Optimistic Optimisation with Exponentially Decaying Regret
BOO achieves exponentially decaying regret O(N^{-√N}) by combining Bayesian optimisation and partitioning-based optimistic optimisation for Matérn GP functions with ν > 4 + D/2.