paper-with-me

Papers

Tight Regret Bounds for Bayesian Optimization in One Dimension

2018-05-30 · ICML 2018 7 · Jonathan Scarlett

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 $\Omega(\sqrt{T})$ and $O(\sqrt{T\log T})$. This gives a tight characterization up to a $\sqrt{\log T}$ factor, and includes the first non-trivial lower bound for noisy BO. Our assumptions are satisfied, for example, by the squared exponential and Mat\'ern-$\nu$ kernels, with the latter requiring $\nu > 2$. Our results certify the near-optimality of existing bounds (Srinivas {\em et al.}, 2009) for the SE kernel, while proving them to be strictly suboptimal for the Mat\'ern kernel with $\nu > 2$.

📄 PDF Abstract BibTeX arXiv:1805.11792

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian Optimization

Methods 이 논문이 사용한 방법론

Gaussian Process Gaussian Processes are non-parametric models for approximating functions. They rely upon a measure of similarity between points (the kernel function) to predict the value for…

Similar Papers 제목 키워드 기반

Tight Regret Bounds for Noisy Optimization of a Brownian Motion

2020-01-25 · Zexin Wang, Vincent Y. F. Tan, Jonathan Scarlett

We consider the problem of Bayesian optimization of a one-dimensional Brownian motion in which the $T$ adaptively chosen observations are corrupted by Gaussian noise. We show that as the smallest possible expected cumula…

Bayesian OptimizationTwo-sample testing

Bayesian Regret Minimization in Offline Bandits

2023-06-02 · Marek Petrik, Guy Tennenholtz, Mohammad Ghavamzadeh

We study how to make decisions that minimize Bayesian regret in offline linear bandits. Prior work suggests that one must take actions with maximum lower confidence bound (LCB) on their reward. We argue that the reliance…

Chained Information-Theoretic bounds and Tight Regret Rate for Linear Bandit Problems

2024-03-05 · Amaury Gouverneur, Borja Rodríguez-Gálvez, Tobias J. Oechtering, Mikael Skoglund

This paper studies the Bayesian regret of a variant of the Thompson-Sampling algorithm for bandit problems. It builds upon the information-theoretic framework of [Russo and Van Roy, 2015] and, more specifically, on the r…

Thompson Sampling

Posterior Sampling-Based Bayesian Optimization with Tighter Bayesian Regret Bounds

2023-11-07 · Shion Takeno, Yu Inatsu, Masayuki Karasuyama, Ichiro Takeuchi

Among various acquisition functions (AFs) in Bayesian optimization (BO), Gaussian process upper confidence bound (GP-UCB) and Thompson sampling (TS) are well-known options with established theoretical properties regardin…

Bayesian OptimizationThompson Sampling

Local Constrained Bayesian Optimization

2026-03-09 · Jing Jingzhe, Fan Zheyi, Szu Hui Ng, Qingpei Hu arxiv

Bayesian optimization (BO) for high-dimensional constrained problems remains a significant challenge due to the curse of dimensionality. We propose Local Constrained Bayesian Optimization (LCBO), a novel framework tailor…