Matches in SemOpenAlex for { <https://semopenalex.org/work/W2996787464> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W2996787464 endingPage "5386" @default.
- W2996787464 startingPage "5379" @default.
- W2996787464 abstract "We study an interesting variant of the stochastic multi-armed bandit problem, which we call the Fair-MAB problem, where, in addition to the objective of maximizing the sum of expected rewards, the algorithm also needs to ensure that at any time, each arm is pulled at least a pre-specified fraction of times. We investigate the interplay between learning and fairness in terms of a pre-specified vector denoting the fractions of guaranteed pulls. We define a fairness-aware regret, which we call r-Regret, that takes into account the above fairness constraints and extends the conventional notion of regret in a natural way. Our primary contribution is to obtain a complete characterization of a class of Fair-MAB algorithms via two parameters: the unfairness tolerance and the learning algorithm used as a black-box. For this class of algorithms, we provide a fairness guarantee that holds uniformly over time, irrespective of the choice of the learning algorithm. Further, when the learning algorithm is UCB1, we show that our algorithm achieves constant r-Regret for a large enough time horizon. Finally, we analyze the cost of fairness in terms of the conventional notion of regret. We conclude by experimentally validating our theoretical results." @default.
- W2996787464 created "2020-01-10" @default.
- W2996787464 creator A5027832422 @default.
- W2996787464 creator A5067928892 @default.
- W2996787464 creator A5068716961 @default.
- W2996787464 creator A5078106294 @default.
- W2996787464 date "2020-04-03" @default.
- W2996787464 modified "2023-09-25" @default.
- W2996787464 title "Achieving Fairness in the Stochastic Multi-Armed Bandit Problem" @default.
- W2996787464 doi "https://doi.org/10.1609/aaai.v34i04.5986" @default.
- W2996787464 hasPublicationYear "2020" @default.
- W2996787464 type Work @default.
- W2996787464 sameAs 2996787464 @default.
- W2996787464 citedByCount "30" @default.
- W2996787464 countsByYear W29967874642019 @default.
- W2996787464 countsByYear W29967874642020 @default.
- W2996787464 countsByYear W29967874642021 @default.
- W2996787464 countsByYear W29967874642022 @default.
- W2996787464 countsByYear W29967874642023 @default.
- W2996787464 crossrefType "journal-article" @default.
- W2996787464 hasAuthorship W2996787464A5027832422 @default.
- W2996787464 hasAuthorship W2996787464A5067928892 @default.
- W2996787464 hasAuthorship W2996787464A5068716961 @default.
- W2996787464 hasAuthorship W2996787464A5078106294 @default.
- W2996787464 hasBestOaLocation W29967874641 @default.
- W2996787464 hasConcept C119857082 @default.
- W2996787464 hasConcept C123197309 @default.
- W2996787464 hasConcept C126255220 @default.
- W2996787464 hasConcept C149629883 @default.
- W2996787464 hasConcept C154945302 @default.
- W2996787464 hasConcept C178790620 @default.
- W2996787464 hasConcept C185592680 @default.
- W2996787464 hasConcept C199360897 @default.
- W2996787464 hasConcept C2777027219 @default.
- W2996787464 hasConcept C2777212361 @default.
- W2996787464 hasConcept C28761237 @default.
- W2996787464 hasConcept C33923547 @default.
- W2996787464 hasConcept C41008148 @default.
- W2996787464 hasConcept C50817715 @default.
- W2996787464 hasConcept C94966114 @default.
- W2996787464 hasConceptScore W2996787464C119857082 @default.
- W2996787464 hasConceptScore W2996787464C123197309 @default.
- W2996787464 hasConceptScore W2996787464C126255220 @default.
- W2996787464 hasConceptScore W2996787464C149629883 @default.
- W2996787464 hasConceptScore W2996787464C154945302 @default.
- W2996787464 hasConceptScore W2996787464C178790620 @default.
- W2996787464 hasConceptScore W2996787464C185592680 @default.
- W2996787464 hasConceptScore W2996787464C199360897 @default.
- W2996787464 hasConceptScore W2996787464C2777027219 @default.
- W2996787464 hasConceptScore W2996787464C2777212361 @default.
- W2996787464 hasConceptScore W2996787464C28761237 @default.
- W2996787464 hasConceptScore W2996787464C33923547 @default.
- W2996787464 hasConceptScore W2996787464C41008148 @default.
- W2996787464 hasConceptScore W2996787464C50817715 @default.
- W2996787464 hasConceptScore W2996787464C94966114 @default.
- W2996787464 hasIssue "04" @default.
- W2996787464 hasLocation W29967874641 @default.
- W2996787464 hasLocation W29967874642 @default.
- W2996787464 hasOpenAccess W2996787464 @default.
- W2996787464 hasPrimaryLocation W29967874641 @default.
- W2996787464 hasRelatedWork W1597250926 @default.
- W2996787464 hasRelatedWork W1841788933 @default.
- W2996787464 hasRelatedWork W2958076322 @default.
- W2996787464 hasRelatedWork W2964073680 @default.
- W2996787464 hasRelatedWork W2996787464 @default.
- W2996787464 hasRelatedWork W3035596066 @default.
- W2996787464 hasRelatedWork W3191284239 @default.
- W2996787464 hasRelatedWork W3200339841 @default.
- W2996787464 hasRelatedWork W4312098146 @default.
- W2996787464 hasRelatedWork W2053041872 @default.
- W2996787464 hasVolume "34" @default.
- W2996787464 isParatext "false" @default.
- W2996787464 isRetracted "false" @default.
- W2996787464 magId "2996787464" @default.
- W2996787464 workType "article" @default.