English
Related papers

Related papers: Statistical Inference under Adaptive Sampling with…

200 papers

Model misspecification is a major consideration in applications of statistical methods and machine learning. However, it is often neglected in contextual bandits. This paper studies a common form of misspecification, an inter-arm…

Machine Learning · Computer Science 2022-10-27 Rong Zhu , Branislav Kveton

Stochastic multi-armed bandits (MABs) provide a fundamental reinforcement learning model to study sequential decision making in uncertain environments. The upper confidence bounds (UCB) algorithm gave birth to the renaissance of bandit…

Machine Learning · Computer Science 2024-06-11 Ambrus Tamás , Szabolcs Szentpéteri , Balázs Csanád Csáji

One of the key drivers of complexity in the classical (stochastic) multi-armed bandit (MAB) problem is the difference between mean rewards in the top two arms, also known as the instance gap. The celebrated Upper Confidence Bound (UCB)…

Machine Learning · Computer Science 2021-10-27 Anand Kalvit , Assaf Zeevi

Adaptive experiments such as multi-arm bandits adapt the treatment-allocation policy and/or the decision to stop the experiment to the data observed so far. This has the potential to improve outcomes for study participants within the…

Methodology · Statistics 2024-05-03 Aurélien Bibaut , Nathan Kallus

We give a new algorithm for best arm identification in linearly parameterised bandits in the fixed confidence setting. The algorithm generalises the well-known LUCB algorithm of Kalyanakrishnan et al. (2012) by playing an arm which…

Machine Learning · Computer Science 2019-11-11 Mohammadi Zaki , Avinash Mohan , Aditya Gopalan

We consider stochastic non-stationary linear bandits where the linear parameter connecting contexts to the reward changes over time. Existing algorithms in this setting localize the policy by gradually discarding or down-weighting past…

Machine Learning · Statistics 2026-03-05 Margherita Lazzaretto , Jonas Peters , Niklas Pfister

Thompson sampling (TS) is widely used for stochastic multi-armed bandits, yet its inferential properties under adaptive data collection are subtle. Classical asymptotic theory for sample means can fail because arm-specific sample sizes are…

Machine Learning · Computer Science 2026-02-06 Shunxing Yan , Han Zhong

In decision-making problems such as the multi-armed bandit, an agent learns sequentially by optimizing a certain feedback. While the mean reward criterion has been extensively studied, other measures that reflect an aversion to adverse…

Machine Learning · Statistics 2023-03-28 Patrick Saux , Odalric-Ambrym Maillard

The Indexed Minimum Empirical Divergence (IMED) algorithm is a highly effective approach that offers a stronger theoretical guarantee of the asymptotic optimality compared to the Kullback--Leibler Upper Confidence Bound (KL-UCB) algorithm…

Machine Learning · Computer Science 2024-05-27 Jie Bian , Vincent Y. F. Tan

We propose $\tt RandUCB$, a bandit strategy that builds on theoretically derived confidence intervals similar to upper confidence bound (UCB) algorithms, but akin to Thompson sampling (TS), it uses randomization to trade off exploration and…

Machine Learning · Computer Science 2020-03-24 Sharan Vaswani , Abbas Mehrabian , Audrey Durand , Branislav Kveton

We introduce two data-driven procedures for optimal estimation and inference in nonparametric models using instrumental variables. The first is a data-driven choice of sieve dimension for a popular class of sieve two-stage least squares…

Econometrics · Economics 2024-01-09 Xiaohong Chen , Timothy Christensen , Sid Kankanala

In this work we revisit two classic high-dimensional online learning problems, namely linear regression and contextual bandits, from the perspective of adversarial robustness. Existing works in algorithmic robust statistics make strong…

Machine Learning · Computer Science 2021-06-14 Sitan Chen , Frederic Koehler , Ankur Moitra , Morris Yau

We provide a simple method to combine stochastic bandit algorithms. Our approach is based on a "meta-UCB" procedure that treats each of $N$ individual bandit algorithms as arms in a higher-level $N$-armed bandit problem that we solve with a…

Machine Learning · Computer Science 2020-12-25 Ashok Cutkosky , Abhimanyu Das , Manish Purohit

Stochastic linear bandits are a natural and simple generalisation of finite-armed bandits with numerous practical applications. Current approaches focus on generalising existing techniques for finite-armed bandits, notably the optimism…

Machine Learning · Statistics 2016-10-17 Tor Lattimore , Csaba Szepesvari

Adaptive sampling schemes are well known to create complex dependence that may invalidate conventional inference methods. A recent line of work shows that this need not be the case for UCB-type algorithms in multi-armed bandits. A central…

Statistics Theory · Mathematics 2026-01-30 Qiyang Han

The principle of optimism in the face of uncertainty is one of the most widely used and successful ideas in multi-armed bandits and reinforcement learning. However, existing optimistic algorithms (primarily UCB and its variants) often…

Machine Learning · Computer Science 2024-03-12 Yunbei Xu , Assaf Zeevi

We study contextual bandits with finitely many actions in which the reward of each arm follows a single-index model with an arm-specific index parameter and an unknown nonparametric link function. We consider a regime in which arms…

Machine Learning · Statistics 2026-03-20 Sakshi Arya , Satarupa Bhattacharjee , Bharath K. Sriperumbudur

Scientific experimentation is largely driven by statistical hypothesis testing to determine significant differences in interventions. Traditionally, experimenters allocate samples uniformly between each intervention. However, such an…

In this paper, we study the behavior of the Upper Confidence Bound-Variance (UCB-V) algorithm for the Multi-Armed Bandit (MAB) problems, a variant of the canonical Upper Confidence Bound (UCB) algorithm that incorporates variance estimates…

Machine Learning · Statistics 2025-02-18 Yingying Fan , Yuxuan Han , Jinchi Lv , Xiaocong Xu , Zhengyuan Zhou

Contextual multi-armed bandits are classical models in reinforcement learning for sequential decision-making associated with individual information. A widely-used policy for bandits is Thompson Sampling, where samples from a data-driven…

Machine Learning · Statistics 2021-11-30 Hongju Park , Mohamad Kazem Shirani Faradonbeh