paper-with-me

홈 › Papers

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 cumulative regret and the smallest possible expected simple regret scale as $\Omega(\sigma\sqrt{T / \log (T)}) \cap \mathcal{O}(\sigma\sqrt{T} \cdot \log T)$ and $\Omega(\sigma / \sqrt{T \log (T)}) \cap \mathcal{O}(\sigma\log T / \sqrt{T})$ respectively, where $\sigma^2$ is the noise variance. Thus, our upper and lower bounds are tight up to a factor of $\mathcal{O}( (\log T)^{1.5} )$. The upper bound uses an algorithm based on confidence bounds and the Markov property of Brownian motion (among other useful properties), and the lower bound is based on a reduction to binary hypothesis testing.

📄 PDF Abstract BibTeX arXiv:2001.09327

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian OptimizationTwo-sample testing

Similar Papers 제목 키워드 기반

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 …

Bayesian Optimization

Optimal Online Learning using Potential Functions

2021-06-20 · Yoav Freund

We study a family of potential functions for online learning. We show that if the potential function has strictly positive derivatives of order 1-4 then the min-max optimal strategy for the adversary is Brownian motion. …

Tight First- and Second-Order Regret Bounds for Adversarial Linear Bandits

2020-12-01 · NeurIPS 2020 12 · Shinji Ito, Shuichi Hirahara, Tasuku Soma, Yuichi Yoshida

We propose novel algorithms with first- and second-order regret bounds for adversarial linear bandits. These regret bounds imply that our algorithms perform well when there is an action achieving a small cumulative loss …

A Unified Analysis Method for Online Optimization in Normed Vector Space

2021-12-22 · Qing-xin Meng, Jian-wei Liu

This paper studies online optimization from a high-level unified theoretical perspective. We not only generalize both Optimistic-DA and Optimistic-MD in normed vector space, but also unify their analysis methods for dyna…

Lower Bounds on Regret for Noisy Gaussian Process Bandit Optimization

2017-05-31 · Jonathan Scarlett, Ilijia Bogunovic, Volkan 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 reproducin…