# Lower Bounds on Regret for Noisy Gaussian Process Bandit Optimization

31 May 2017Jonathan ScarlettIlijia BogunovicVolkan Cevher

In this paper, we consider the problem of sequentially optimizing a black-box function $f$ based on noisy samples and bandit feedback. We assume that $f$ is smooth in the sense of having a bounded norm in some reproducing kernel Hilbert space (RKHS), yielding a commonly-considered non-Bayesian form of Gaussian process bandit optimization... (read more)

PDF Abstract

No code implementations yet. Submit your code now