English
Related papers

Related papers: A Linear Bandit for Seasonal Environments

200 papers

We introduce data-driven decision-making algorithms that achieve state-of-the-art \emph{dynamic regret} bounds for non-stationary bandit settings. These settings capture applications such as advertisement allocation, dynamic pricing, and…

Machine Learning · Computer Science 2021-03-19 Wang Chi Cheung , David Simchi-Levi , Ruihao Zhu

The contextual bandit has been identified as a powerful framework to formulate the recommendation process as a sequential decision-making process, where each item is regarded as an arm and the objective is to minimize the regret of $T$…

Machine Learning · Computer Science 2024-09-30 Yikun Ban , Yunzhe Qi , Tianxin Wei , Lihui Liu , Jingrui He

We consider a novel formulation of the multi-armed bandit model, which we call the contextual bandit with restricted context, where only a limited number of features can be accessed by the learner at every iteration. This novel formulation…

Artificial Intelligence · Computer Science 2017-06-09 Djallel Bouneffouf , Irina Rish , Guillermo A. Cecchi , Raphael Feraud

We study constrained contextual bandits (CCB) with adversarially chosen contexts, where each action yields a random reward and incurs a random cost. We adopt the standard realizability assumption: conditioned on the observed context,…

Machine Learning · Computer Science 2026-02-06 Dhruv Sarkar , Abhishek Sinha

In networked environments, users frequently share recommendations about content, products, services, and courses of action with others. The extent to which such recommendations are successful and adopted is highly contextual, dependent on…

Machine Learning · Computer Science 2025-10-23 Ahmed Sayeed Faruk , Mohammad Shahverdikondori , Elena Zheleva

We design and implement an adaptive experiment (a ``contextual bandit'') to learn a targeted treatment assignment policy, where the goal is to use a participant's survey responses to determine which charity to expose them to in a donation…

Contextual Bandit (CB) algorithms are widely adopted for personalized recommendations but often struggle in dynamic environments typical of fantasy sports, where rapid changes in user behavior and dramatic shifts in reward distributions due…

Machine Learning · Computer Science 2026-01-22 Anupam Agrawal , Rajesh Mohanty , Shamik Bhattacharjee , Abhimanyu Mittal

We analyze the unintended effects that recommender systems have on the preferences of users that they are learning. We consider a contextual multi-armed bandit recommendation algorithm that learns optimal product recommendations based on…

Machine Learning · Computer Science 2026-02-11 Prabhat Lankireddy , Jayakrishnan Nair , D Manjunath

We consider the linear contextual bandit problem with resource consumption, in addition to reward generation. In each round, the outcome of pulling an arm is a reward as well as a vector of resource consumptions. The expected values of…

Machine Learning · Computer Science 2016-07-12 Shipra Agrawal , Nikhil R. Devanur

Most existing approaches in Context-Aware Recommender Systems (CRS) focus on recommending relevant items to users taking into account contextual information, such as time, location, or social aspects. However, few of them have considered…

Information Retrieval · Computer Science 2014-04-01 Djallel Bouneffouf

Contextual bandit algorithms have transformed modern experimentation by enabling real-time adaptation for personalized treatment and efficient use of data. Yet these advantages create challenges for statistical inference due to adaptivity.…

Statistics Theory · Mathematics 2025-09-23 Yongyi Guo , Ziping Xu

We study a nonparametric contextual bandit problem where the expected reward functions belong to a H\"older class with smoothness parameter $\beta$. We show how this interpolates between two extremes that were previously studied in…

Machine Learning · Statistics 2020-09-14 Yichun Hu , Nathan Kallus , Xiaojie Mao

In production systems, contextual bandit approaches often rely on direct reward models that take both action and context as input. However, these models can suffer from confounding, making it difficult to isolate the effect of the action…

Machine Learning · Computer Science 2025-09-16 Alexandre Gilotte , Otmane Sakhi , Imad Aouali , Benjamin Heymann

In the classical contextual bandits problem, in each round $t$, a learner observes some context $c$, chooses some action $i$ to perform, and receives some reward $r_{i,t}(c)$. We consider the variant of this problem where in addition to…

Machine Learning · Computer Science 2021-11-17 Santiago Balseiro , Negin Golrezaei , Mohammad Mahdian , Vahab Mirrokni , Jon Schneider

The stochastic multi-armed bandit setting has been recently studied in the non-stationary regime, where the mean payoff of each action is a non-decreasing function of the number of rounds passed since it was last played. This model captures…

Machine Learning · Computer Science 2022-10-13 Orestis Papadigenopoulos , Constantine Caramanis , Sanjay Shakkottai

Most bandit policies are designed to either minimize regret in any problem instance, making very few assumptions about the underlying environment, or in a Bayesian sense, assuming a prior distribution over environment parameters. The former…

Machine Learning · Computer Science 2021-01-07 Branislav Kveton , Martin Mladenov , Chih-Wei Hsu , Manzil Zaheer , Csaba Szepesvari , Craig Boutilier

Multi-armed bandit problems are receiving a great deal of attention because they adequately formalize the exploration-exploitation trade-offs arising in several industrially relevant applications, such as online advertisement and, more…

Machine Learning · Computer Science 2013-11-05 Nicolò Cesa-Bianchi , Claudio Gentile , Giovanni Zappella

We study incentivized exploration for the multi-armed bandit (MAB) problem with non-stationary reward distributions, where players receive compensation for exploring arms other than the greedy choice and may provide biased feedback on the…

Machine Learning · Computer Science 2024-03-19 Sourav Chakraborty , Lijun Chen

We study nonparametric contextual bandits under batch constraints, where the expected reward for each action is modeled as a smooth function of covariates, and the policy updates are made at the end of each batch of observations. We…

Statistics Theory · Mathematics 2025-10-06 Rong Jiang , Cong Ma

Contextual bandits with average-case statistical guarantees are inadequate in risk-averse situations because they might trade off degraded worst-case behaviour for better average performance. Designing a risk-averse contextual bandit is…

Machine Learning · Statistics 2023-07-11 Mónika Farsang , Paul Mineiro , Wangda Zhang