English
Related papers

Related papers: Regret Bounds for Thompson Sampling in Episodic Re…

200 papers

A challenging aspect of the bandit problem is that a stochastic reward is observed only for the chosen arm and the rewards of other arms remain missing. The dependence of the arm choice on the past context and reward pairs compounds the…

Machine Learning · Statistics 2023-05-02 Wonyoung Kim , Gi-soo Kim , Myunghee Cho Paik

We study the stochastic multi-armed bandit problem and design new policies that enjoy both worst-case optimality for expected regret and light-tailed risk for regret distribution. Specifically, our policy design (i) enjoys the worst-case…

Machine Learning · Statistics 2024-07-23 David Simchi-Levi , Zeyu Zheng , Feng Zhu

We study the dynamic regret of multi-armed bandit and experts problem in non-stationary stochastic environments. We introduce a new parameter $\Lambda$, which measures the total statistical variance of the loss distributions over $T$ rounds…

Machine Learning · Computer Science 2019-06-24 Chen-Yu Wei , Yi-Te Hong , Chi-Jen Lu

In multi-armed bandit problems, the typical goal is to identify the arm with the highest reward. This paper explores a threshold-based bandit problem, aiming to select an arm based on its relation to a prescribed threshold \(\tau \). We…

Machine Learning · Computer Science 2025-09-03 Chanakya Varude , Jay Chaudhary , Siddharth Kaushik , Prasanna Chaporkar

Given a multi-armed bandit problem it may be desirable to achieve a smaller-than-usual worst-case regret for some special actions. I show that the price for such unbalanced worst-case regret guarantees is rather high. Specifically, if an…

Machine Learning · Computer Science 2015-11-03 Tor Lattimore

We consider a bandit optimization problem for nonconvex and non-smooth functions, where in each trial the loss function is the sum of a linear function and a small but arbitrary perturbation chosen after observing the player's choice. We…

Machine Learning · Computer Science 2026-01-07 Zhuoyu Cheng , Kohei Hatano , Eiji Takimoto

Information-directed sampling (IDS) is a powerful framework for solving bandit problems which has shown strong results in both Bayesian and frequentist settings. However, frequentist IDS, like many other bandit algorithms, requires that one…

Machine Learning · Statistics 2025-03-10 Piotr M. Suder , Eric Laber

Bayesian bandits using Thompson Sampling have seen increasing success in recent years. Yet existing value models (of rewards) are misspecified on many real-world problem. We demonstrate this on the User Experience Optimization (UXO)…

Machine Learning · Computer Science 2020-10-09 Mack Sweeney , Matthew van Adelsberg , Kathryn Laskey , Carlotta Domeniconi

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…

Machine Learning · Computer Science 2023-07-21 Chong Liu , Ming Yin , Yu-Xiang Wang

Mode estimation is a classical problem in statistics with a wide range of applications in machine learning. Despite this, there is little understanding in its robustness properties under possibly adversarial data contamination. In this…

Machine Learning · Computer Science 2020-03-09 Aldo Pacchiano , Heinrich Jiang , Michael I. Jordan

We introduce contextual queueing bandits, a new context-aware framework for scheduling while simultaneously learning unknown service rates. Individual jobs carry heterogeneous contextual features, based on which the agent chooses a job and…

Machine Learning · Computer Science 2026-05-19 Seoungbin Bae , Garyeong Kang , Dabeen Lee

Influence maximization, adaptive routing, and dynamic spectrum allocation all require choosing the right action from a large set of alternatives. Thanks to the advances in combinatorial optimization, these and many similar problems can be…

Machine Learning · Computer Science 2020-12-29 Alihan Hüyük , Cem Tekin

We study the regret of Thompson sampling (TS) algorithms for exponential family bandits, where the reward distribution is from a one-dimensional exponential family, which covers many common reward distributions including Bernoulli,…

Machine Learning · Statistics 2022-06-09 Tianyuan Jin , Pan Xu , Xiaokui Xiao , Anima Anandkumar

We consider a situation where an agent has $T$ ressources to be allocated to a larger number $N$ of actions. Each action can be completed at most once and results in a stochastic reward with unknown mean. The goal of the agent is to…

Statistics Theory · Mathematics 2020-11-04 Solenne Gaucher

We consider the classical stochastic multi-armed bandit but where, from time to time and roughly with frequency $\epsilon$, an extra observation is gathered by the agent for free. We prove that, no matter how small $\epsilon$ is the agent…

Machine Learning · Computer Science 2018-07-11 Rémy Degenne , Evrard Garcelon , Vianney Perchet

We study the contextual multi-armed bandit problem with a finite context space (a.k.a. subpopulations), where the learner recommends a best action for each context and is evaluated by context-weighted simple regret. Our guarantees are…

Machine Learning · Computer Science 2026-05-20 Mohammad Shahverdikondori , Jalal Etesami , Negar Kiyavash

In the classical multi-armed bandit problem, instance-dependent algorithms attain improved performance on "easy" problems with a gap between the best and second-best arm. Are similar guarantees possible for contextual bandits? While…

Machine Learning · Computer Science 2020-10-08 Dylan J. Foster , Alexander Rakhlin , David Simchi-Levi , Yunzong Xu

Bandit-style algorithms have been studied extensively in stochastic and adversarial settings. Such algorithms have been shown to be useful in multiplayer settings, e.g. to solve the wireless network selection problem, which can be…

Networking and Internet Architecture · Computer Science 2019-04-30 Shunhao Oh , Anuja Meetoo Appavoo , Seth Gilbert

We study the problem of worst case regret in piecewise stationary multi armed bandits. While the minimax theory for stationary bandits is well established, understanding analogous limits in time-varying settings is challenging. Existing…

Machine Learning · Computer Science 2025-11-11 Gal Mendelson , Eyal Tadmor

Thompson sampling is one of the earliest randomized algorithms for multi-armed bandits (MAB). In this paper, we extend the Thompson sampling to Budgeted MAB, where there is random cost for pulling an arm and the total cost is constrained by…

Machine Learning · Computer Science 2015-05-04 Yingce Xia , Haifang Li , Tao Qin , Nenghai Yu , Tie-Yan Liu