Bayesian Optimization with Exponential Convergence
This addresses a key bottleneck in Bayesian optimization for practitioners by making it more efficient and easier to implement.
The paper tackles the problem of Bayesian optimization methods requiring auxiliary optimization and delta-cover sampling, which are time-consuming and impractical, and presents a method that eliminates both requirements while achieving exponential convergence.
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.