Results 11 to 20 of about 492,986 (210)
Batched Nonparametric Contextual Bandits [PDF]
IEEE Transactions on Information TheoryWe 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.
Ma, Cong, Jiang, Rong
core +6 more sources
Balanced Linear Contextual Bandits
Proceedings of the AAAI Conference on Artificial Intelligence, 2019 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 estimation problems
Dimakopoulou, Maria +3 more
core +5 more sources
Thompson Sampling Regret Bounds for Contextual Bandits with sub-Gaussian rewards [PDF]
, 2023 In this work, we study the performance of the Thompson Sampling algorithm for Contextual Bandit problems based on the framework introduced by [1] and their concept of lifted information ratio.
Rodríguez Gálvez, Borja, +3 more
core +3 more sources
On Submodular Contextual Bandits
CoRR, 2021 We consider the problem of contextual bandits where actions are subsets of a ground set and mean rewards are modeled by an unknown monotone submodular function that belongs to a class $\mathcal{F}$. We allow time-varying matroid constraints to be placed on the feasible sets.
Dean P. Foster, Alexander Rakhlin
openaire +3 more sources
Smoothness-Adaptive Contextual Bandits [PDF]
Operations Research, 2021 We study a non-parametric multi-armed bandit problem with stochastic covariates, where a key complexity driver is the smoothness of payoff functions with respect to covariates. Previous studies have focused on deriving minimax-optimal algorithms in cases where it is a priori known how smooth the payoff functions are.
Yonatan Gur +2 more
openaire +3 more sources
Achieving User-Side Fairness in Contextual Bandits
Human-Centric Intelligent Systems, 2022 Personalized recommendation based on multi-arm bandit (MAB) algorithms has shown to lead to high utility and efficiency as it can dynamically adapt the recommendation strategy based on feedback.
Wen Huang +4 more
doaj +1 more source
2022 IEEE International Symposium on Information Theory (ISIT), 2022 We consider a remote contextual multi-armed bandit (CMAB) problem, in which the decision-maker observes the context and the reward, but must communicate the actions to be taken by the agents over a rate-limited communication channel. This can model, for example, a personalized ad placement application, where the content owner observes the individual ...
Francesco Pase +2 more
openaire +4 more sources
Selectively Contextual Bandits
CoRR, 2022 Contextual bandits are widely used in industrial personalization systems. These online learning frameworks learn a treatment assignment policy in the presence of treatment effects that vary with the observed contextual features of the users. While personalization creates a rich user experience that reflect individual interests, there are benefits of a ...
Claudia V. Roberts +4 more
openaire +3 more sources
Action Centered Contextual Bandits. [PDF]
Adv Neural Inf Process Syst, 2017 to appear at NIPS ...
Greenewald K +3 more
europepmc +5 more sources
Contextual combinatorial conservative bandits
Theoretical Computer Science, 2023 The problem of multi-armed bandits (MAB) asks to make sequential decisions while balancing between exploitation and exploration, and have been successfully applied to a wide range of practical scenarios. Various algorithms have been designed to achieve a high reward in a long term.
Xiaojin Zhang +3 more
openaire +4 more sources