中文
相关论文

相关论文: On the Sublinear Regret of GP-UCB

200 篇论文

We study how to learn optimal interventions sequentially given causal information represented as a causal graph along with associated conditional distributions. Causal modeling is useful in real world problems like online advertisement…

机器学习 · 统计学 2020-06-12 Yangyi Lu , Amirhossein Meisami , Ambuj Tewari , Zhenyu Yan

We study the linear contextual bandit problem with finite action sets. When the problem dimension is $d$, the time horizon is $T$, and there are $n \leq 2^{d/2}$ candidate actions per time period, we (1) show that the minimax expected…

机器学习 · 统计学 2020-08-20 Yingkai Li , Yining Wang , Yuan Zhou

In this paper, we consider algorithm-independent lower bounds for the problem of black-box optimization of functions having a bounded norm is some Reproducing Kernel Hilbert Space (RKHS), which can be viewed as a non-Bayesian Gaussian…

机器学习 · 统计学 2021-05-25 Xu Cai , Jonathan Scarlett

Upper Confidence Bound (UCB) is arguably the most commonly used method for linear multi-arm bandit problems. While conceptually and computationally simple, this method highly relies on the confidence bounds, failing to strike the optimal…

机器学习 · 计算机科学 2020-06-05 Kaige Yang , Laura Toni

We study fine-grained gap-dependent regret bounds for model-free reinforcement learning in episodic tabular Markov Decision Processes. Existing model-free algorithms achieve minimax worst-case regret, but their gap-dependent bounds remain…

机器学习 · 统计学 2025-10-09 Haochen Zhang , Zhong Zheng , Lingzhou Xue

In many scientific and engineering applications, we are tasked with the maximisation of an expensive to evaluate black box function $f$. Traditional settings for this problem assume just the availability of this single function. However, in…

We study a widely used Bayesian optimization method, Gaussian process Thompson sampling (GP-TS), under the assumption that the objective function is a sample path from a GP. Compared with the GP upper confidence bound (GP-UCB) with…

机器学习 · 统计学 2026-03-11 Shion Takeno , Shogo Iwazaki

Cascading bandit (CB) is a popular model for web search and online advertising, where an agent aims to learn the $K$ most attractive items out of a ground set of size $L$ during the interaction with a user. However, the stationary CB model…

机器学习 · 计算机科学 2020-02-18 Lingda Wang , Huozhi Zhou , Bingcong Li , Lav R. Varshney , Zhizhen Zhao

We study linear bandits when the underlying reward function is not linear. Existing work relies on a uniform misspecification parameter $\epsilon$ that measures the sup-norm error of the best linear approximation. This results in an…

机器学习 · 计算机科学 2023-07-21 Chong Liu , Ming Yin , Yu-Xiang Wang

We study collaborative learning among distributed clients facilitated by a central server. Each client is interested in maximizing a personalized objective function that is a weighted sum of its local objective and a global objective. Each…

机器学习 · 统计学 2023-04-18 Sudeep Salgia , Sattar Vakili , Qing Zhao

The goal of this paper is to characterize Gaussian-Process optimization in the setting where the function domain is large relative to the number of admissible function evaluations, i.e., where it is impossible to find the global optimum. We…

机器学习 · 计算机科学 2022-01-26 Manuel Wüthrich , Bernhard Schölkopf , Andreas Krause

Sequential optimization of black-box functions from noisy evaluations has been widely studied, with Gaussian Process bandit algorithms such as GP-UCB guaranteeing no-regret in stationary settings. However, for time-varying objectives, it is…

机器学习 · 统计学 2025-12-04 Eliabelle Mauduit , Eloïse Berthier , Andrea Simonetto

Multi-armed bandit algorithms provide solutions for sequential decision-making where learning takes place by interacting with the environment. In this work, we model a distributed optimization problem as a multi-agent kernelized multi-armed…

机器学习 · 计算机科学 2023-12-11 Ayush Rai , Shaoshuai Mou

Bayesian optimization (BO) is a widely used iterative black-box optimization method that utilizes Gaussian process (GP) surrogate models. In practice, BO is typically terminated after a fixed evaluation budget is exhausted, which can incur…

机器学习 · 计算机科学 2026-05-22 Haowei Wang , Jingyi Wang , Qiyu Wei

In federated multi-armed bandit problems, maximizing global reward while satisfying minimum privacy requirements to protect clients is the main goal. To formulate such problems, we consider a combinatorial contextual bandit setting with…

机器学习 · 计算机科学 2023-07-11 Sepehr Elahi , Baran Atalar , Sevda Öğüt , Cem Tekin

Several optimism-based stochastic bandit algorithms -- including UCB, UCB-V, linear UCB, and finite-arm GP-UCB -- achieve logarithmic regret using proofs that, despite superficial differences, follow essentially the same structure. This…

机器学习 · 计算机科学 2025-12-23 Vikram Krishnamurthy

We investigate the piecewise-stationary combinatorial semi-bandit problem. Compared to the original combinatorial semi-bandit problem, our setting assumes the reward distributions of base arms may change in a piecewise-stationary manner at…

机器学习 · 计算机科学 2020-02-24 Huozhi Zhou , Lingda Wang , Lav R. Varshney , Ee-Peng Lim

The paper considers the problem of global optimization in the setup of stochastic process bandits. We introduce an UCB algorithm which builds a cascade of discretization trees based on generic chaining in order to render possible his…

机器学习 · 统计学 2016-02-22 Emile Contal , Nicolas Vayatis

The expected improvement (EI) algorithm is one of the most popular strategies for optimization under uncertainty due to its simplicity and efficiency. Despite its popularity, the theoretical aspects of this algorithm have not been properly…

机器学习 · 计算机科学 2026-04-28 Hung Tran-The , Sunil Gupta , Santu Rana , Svetha Venkatesh

Safety is a desirable property that can immensely increase the applicability of learning algorithms in real-world decision-making problems. It is much easier for a company to deploy an algorithm that is safe, i.e., guaranteed to perform at…

机器学习 · 统计学 2017-03-07 Abbas Kazerouni , Mohammad Ghavamzadeh , Yasin Abbasi-Yadkori , Benjamin Van Roy