Tight Regret Bounds for Bayesian Optimization in One Dimension

05/30/2018
by   Jonathan Scarlett, et al.
0

We consider the problem of Bayesian optimization (BO) in one dimension, under a Gaussian process prior and Gaussian sampling noise. We provide a theoretical analysis showing that, under fairly mild technical assumptions on the kernel, the best possible cumulative regret up to time T behaves as Ω(√(T)) and O(√(T T)). This gives a tight characterization up to a √( T) factor, and includes the first non-trivial lower bound for noisy BO. Our assumptions are satisfied, for example, by the squared exponential and Matérn-ν kernels, with the latter requiring ν > 2. Our results certify the near-optimality of existing bounds (Srinivas et al., 2009) for the SE kernel, while proving them to be strictly suboptimal for the Matérn kernel with ν > 2.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/16/2019

Bayesian Optimization under Heavy-tailed Payoffs

We consider black box optimization of an unknown function in the nonpara...
research
01/25/2020

Tight Regret Bounds for Noisy Optimization of a Brownian Motion

We consider the problem of Bayesian optimization of a one-dimensional Br...
research
02/12/2020

Regret Bounds for Noise-Free Bayesian Optimization

Bayesian optimisation is a powerful method for non-convex black-box opti...
research
03/04/2022

Distributionally Robust Bayesian Optimization with φ-divergences

The study of robustness has received much attention due to its inevitabi...
research
02/01/2022

Meta-Learning Hypothesis Spaces for Sequential Decision-making

Obtaining reliable, adaptive confidence sets for prediction functions (h...
research
05/10/2022

Adjusted Expected Improvement for Cumulative Regret Minimization in Noisy Bayesian Optimization

The expected improvement (EI) is one of the most popular acquisition fun...
research
06/27/2012

Exponential Regret Bounds for Gaussian Process Bandits with Deterministic Observations

This paper analyzes the problem of Gaussian process (GP) bandits with de...

Please sign up or login with your details

Forgot password? Click here to reset