Achieving fairness in the stochastic multi-armed bandit problem

MaRDI QIDQ5159459zbMATH OpenFDO

Authors Vishakha Patil, Ganesh Ghalme, Vineet Nair, Y. Narahari

Publication date 27 October 2021

Full work available at URL https://arxiv.org/abs/1907.10516, https://jmlr.csail.mit.edu/papers/v22/20-704.html

zbMATH Keywords

fairnessmachine learningmulti-armed banditsonline learningreinforcement learningupper confidence bounds

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Mechanisms with learning for stochastic multi-armed bandit problems
• Constrained regret minimization for multi-criterion multi-armed bandits
• Regret analysis of stochastic and nonstochastic multi-armed bandit problems
• UCB revisited: improved regret bounds for the stochastic multi-armed bandit problem

Cites work

• Advancing subgroup fairness via sleeping experts
• Bandit algorithms
• Bandits with knapsacks
• Fairness through awareness
• Finite-time analysis of the multiarmed bandit problem
• Introduction to multi-armed bandits
• Ranking with Fairness Constraints
• Regret analysis of stochastic and nonstochastic multi-armed bandit problems
• Regret bounds for sleeping experts and bandits

Cited in

(7)

• On fair selection in the presence of implicit and differential variance
• Fairness in learning-based sequential decision algorithms: a survey
• Achieving Optimal Fairness from Biased Coinflips
• Individual fairness in hindsight
• Multi-armed linear bandits with latent biases
• Risk preferences of learning algorithms
• Combinatorial multi-armed bandits with fairness constraints: an online convex optimization perspective

This page was built for publication: Achieving fairness in the stochastic multi-armed bandit problem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5159459)