English
Related papers

Related papers: Instance-Sensitive Algorithms for Pure Exploration…

200 papers

Bandit algorithms solve diverse sequential decision-making problems, but are often too sample-inefficient for from-scratch personalization. To substantially reduce exploration times, latent bandit algorithms exploit cross-instance structure…

Machine Learning · Computer Science 2026-05-11 Emil Carlsson , Newton Mwai , Fredrik D. Johansson

Contextual bandit learning is an increasingly popular approach to optimizing recommender systems via user feedback, but can be slow to converge in practice due to the need for exploring a large feature space. In this paper, we propose a…

Machine Learning · Computer Science 2012-07-03 Yisong Yue , Sue Ann Hong , Carlos Guestrin

Reward-biased maximum likelihood estimation (RBMLE) is a classic principle in the adaptive control literature for tackling explore-exploit trade-offs. This paper studies the stochastic contextual bandit problem with general bounded reward…

Machine Learning · Computer Science 2022-05-31 Yu-Heng Hung , Ping-Chun Hsieh

Bandit algorithms are guaranteed to solve diverse sequential decision-making problems, provided that a sufficient exploration budget is available. However, learning from scratch is often too costly for personalization tasks where a single…

Machine Learning · Computer Science 2025-08-08 Newton Mwai , Emil Carlsson , Fredrik D. Johansson

We introduce a novel algorithmic approach to content recommendation based on adaptive clustering of exploration-exploitation ("bandit") strategies. We provide a sharp regret analysis of this algorithm in a standard stochastic noise setting,…

Machine Learning · Computer Science 2014-06-09 Claudio Gentile , Shuai Li , Giovanni Zappella

Contextual bandit algorithms are sensitive to the estimation method of the outcome model as well as the exploration method used, particularly in the presence of rich heterogeneity or complex outcome models, which can lead to difficult…

Machine Learning · Statistics 2018-12-18 Maria Dimakopoulou , Zhengyuan Zhou , Susan Athey , Guido Imbens

We introduce a bandit framework for stochastic matching under the multinomial logit (MNL) choice model. In our setting, $N$ agents on one side are assigned to $K$ arms on the other side, where each arm stochastically selects an agent from…

Machine Learning · Statistics 2026-01-30 Jung-hun Kim , Min-hwan Oh

Multi-Armed Bandit (MAB) algorithms are widely used in recommender systems that require continuous, incremental learning. A core aspect of MABs is the exploration-exploitation trade-off: choosing between exploiting items likely to be…

Machine Learning · Computer Science 2026-04-20 Pedro R. Pires , Gregorio F. Azevedo , Pietro L. Campos , Rafael T. Sereicikas , Tiago A. Almeida

We consider the contextual bandit problem, where a player sequentially makes decisions based on past observations to maximize the cumulative reward. Although many algorithms have been proposed for contextual bandit, most of them rely on…

Machine Learning · Computer Science 2021-06-08 Qin Ding , Cho-Jui Hsieh , James Sharpnack

Effective exploration is believed to positively influence the long-term user experience on recommendation platforms. Determining its exact benefits, however, has been challenging. Regular A/B tests on exploration often measure neutral or…

We propose the first fully-adaptive algorithm for pure exploration in linear bandits---the task to find the arm with the largest expected reward, which depends on an unknown parameter linearly. While existing methods partially or entirely…

Machine Learning · Statistics 2017-10-17 Liyuan Xu , Junya Honda , Masashi Sugiyama

Despite the great interest in the bandit problem, designing efficient algorithms for complex models remains challenging, as there is typically no analytical way to quantify uncertainty. In this paper, we propose Multiplier Bootstrap-based…

Machine Learning · Computer Science 2023-02-06 Runzhe Wan , Haoyu Wei , Branislav Kveton , Rui Song

We provide a sound and consistent foundation for the use of \emph{nonrandom} exploration data in "contextual bandit" or "partially labeled" settings where only the value of a chosen action is learned. The primary challenge in a variety of…

Machine Learning · Computer Science 2010-06-15 Alex Strehl , John Langford , Sham Kakade , Lihong Li

We propose a contextual bandit based model to capture the learning and social welfare goals of a web platform in the presence of myopic users. By using payments to incentivize these agents to explore different items/recommendations, we show…

Machine Learning · Computer Science 2020-01-23 Priyank Agrawal , Theja Tulabandhula

In this paper, we study the non-asymptotic sample complexity for the pure exploration problem in contextual bandits and tabular reinforcement learning (RL): identifying an epsilon-optimal policy from a set of policies with high probability.…

Machine Learning · Computer Science 2024-06-12 Adhyyan Narang , Andrew Wagenmaker , Lillian Ratliff , Kevin Jamieson

We study the problem of pure exploration in matching markets under uncertain preferences, where the goal is to identify a stable matching with confidence parameter $\delta$ and minimal sample complexity. Agents learn preferences via…

Computer Science and Game Theory · Computer Science 2025-09-19 Tejas Pagare , Agniv Bandyopadhyay , Sandeep Juneja

In real-world streaming recommender systems, user preferences evolve dynamically over time. Existing bandit-based methods treat time merely as a timestamp, neglecting its explicit relationship with user preferences and leading to suboptimal…

Machine Learning · Computer Science 2026-02-10 Chenglei Shen , Yi Zhan , Weijie Yu , Xiao Zhang , Jun Xu

Contextual bandits have emerged as a cornerstone in reinforcement learning, enabling systems to make decisions with partial feedback. However, as contexts grow in complexity, traditional bandit algorithms can face challenges in adequately…

Machine Learning · Computer Science 2023-11-07 Ali Baheri , Cecilia O. Alm

We present a new algorithm based on an gradient ascent for a general Active Exploration bandit problem in the fixed confidence setting. This problem encompasses several well studied problems such that the Best Arm Identification or…

Machine Learning · Statistics 2019-05-21 Pierre Ménard

Contextual bandits are widely-used in the study of learning-based control policies for finite action spaces. While the problem is well-studied for bandits with perfectly observed context vectors, little is known about the case of…

Machine Learning · Statistics 2022-02-03 Hongju Park , Mohamad Kazem Shirani Faradonbeh