FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2964860107> ?p ?o ?g. }

• W2964860107 endingPage "540" @default.
• W2964860107 startingPage "530" @default.
• W2964860107 abstract "We propose a new online algorithm for minimizing the cumulative regret in stochastic linear bandits. The key idea is to build a perturbed history, which mixes the history of observed rewards with a pseudo-history of randomly generated i.i.d. pseudo-rewards. Our algorithm, perturbed-history exploration in a linear bandit (LinPHE), estimates a linear model from its perturbed history and pulls the arm with the highest value under that model. We prove a $tilde{O}(d sqrt{n})$ gap-free bound on the expected $n$-round regret of LinPHE, where $d$ is the number of features. Our analysis relies on novel concentration and anti-concentration bounds on the weighted sum of Bernoulli random variables. To show the generality of our design, we extend LinPHE to a logistic reward model. We evaluate both algorithms empirically and show that they are practical." @default.
• W2964860107 created "2019-08-13" @default.
• W2964860107 creator A5013843778 @default.
• W2964860107 creator A5036934218 @default.
• W2964860107 creator A5049020775 @default.
• W2964860107 creator A5069856068 @default.
• W2964860107 date "2019-03-01" @default.
• W2964860107 modified "2023-10-05" @default.
• W2964860107 title "Perturbed-History Exploration in Stochastic Linear Bandits." @default.
• W2964860107 cites W148122774 @default.
• W2964860107 cites W1579979603 @default.
• W2964860107 cites W1687382548 @default.
• W2964860107 cites W2029604041 @default.
• W2964860107 cites W2039522160 @default.
• W2964860107 cites W2108738385 @default.
• W2964860107 cites W2119738618 @default.
• W2964860107 cites W2141645258 @default.
• W2964860107 cites W2152828142 @default.
• W2964860107 cites W2165856466 @default.
• W2964860107 cites W2166253248 @default.
• W2964860107 cites W2168405694 @default.
• W2964860107 cites W2312609093 @default.
• W2964860107 cites W2621143418 @default.
• W2964860107 cites W2625190553 @default.
• W2964860107 cites W268671474 @default.
• W2964860107 cites W2804585439 @default.
• W2964860107 cites W2950064235 @default.
• W2964860107 cites W2962755588 @default.
• W2964860107 cites W2963007936 @default.
• W2964860107 cites W2964330179 @default.
• W2964860107 cites W3037875958 @default.
• W2964860107 cites W50486269 @default.
• W2964860107 hasPublicationYear "2019" @default.
• W2964860107 type Work @default.
• W2964860107 sameAs 2964860107 @default.
• W2964860107 citedByCount "6" @default.
• W2964860107 countsByYear W29648601072018 @default.
• W2964860107 countsByYear W29648601072019 @default.
• W2964860107 countsByYear W29648601072020 @default.
• W2964860107 countsByYear W29648601072021 @default.
• W2964860107 crossrefType "proceedings-article" @default.
• W2964860107 hasAuthorship W2964860107A5013843778 @default.
• W2964860107 hasAuthorship W2964860107A5036934218 @default.
• W2964860107 hasAuthorship W2964860107A5049020775 @default.
• W2964860107 hasAuthorship W2964860107A5069856068 @default.
• W2964860107 hasConcept C105795698 @default.
• W2964860107 hasConcept C114614502 @default.
• W2964860107 hasConcept C126255220 @default.
• W2964860107 hasConcept C127413603 @default.
• W2964860107 hasConcept C146978453 @default.
• W2964860107 hasConcept C152361515 @default.
• W2964860107 hasConcept C162324750 @default.
• W2964860107 hasConcept C187736073 @default.
• W2964860107 hasConcept C26517878 @default.
• W2964860107 hasConcept C2776291640 @default.
• W2964860107 hasConcept C2780767217 @default.
• W2964860107 hasConcept C28826006 @default.
• W2964860107 hasConcept C33923547 @default.
• W2964860107 hasConcept C36686422 @default.
• W2964860107 hasConcept C38652104 @default.
• W2964860107 hasConcept C41008148 @default.
• W2964860107 hasConcept C50817715 @default.
• W2964860107 hasConceptScore W2964860107C105795698 @default.
• W2964860107 hasConceptScore W2964860107C114614502 @default.
• W2964860107 hasConceptScore W2964860107C126255220 @default.
• W2964860107 hasConceptScore W2964860107C127413603 @default.
• W2964860107 hasConceptScore W2964860107C146978453 @default.
• W2964860107 hasConceptScore W2964860107C152361515 @default.
• W2964860107 hasConceptScore W2964860107C162324750 @default.
• W2964860107 hasConceptScore W2964860107C187736073 @default.
• W2964860107 hasConceptScore W2964860107C26517878 @default.
• W2964860107 hasConceptScore W2964860107C2776291640 @default.
• W2964860107 hasConceptScore W2964860107C2780767217 @default.
• W2964860107 hasConceptScore W2964860107C28826006 @default.
• W2964860107 hasConceptScore W2964860107C33923547 @default.
• W2964860107 hasConceptScore W2964860107C36686422 @default.
• W2964860107 hasConceptScore W2964860107C38652104 @default.
• W2964860107 hasConceptScore W2964860107C41008148 @default.
• W2964860107 hasConceptScore W2964860107C50817715 @default.
• W2964860107 hasLocation W29648601071 @default.
• W2964860107 hasOpenAccess W2964860107 @default.
• W2964860107 hasPrimaryLocation W29648601071 @default.
• W2964860107 hasRelatedWork W2028404160 @default.
• W2964860107 hasRelatedWork W2039522160 @default.
• W2964860107 hasRelatedWork W2592998600 @default.
• W2964860107 hasRelatedWork W2616001803 @default.
• W2964860107 hasRelatedWork W2622407839 @default.
• W2964860107 hasRelatedWork W2896133671 @default.
• W2964860107 hasRelatedWork W2951590424 @default.
• W2964860107 hasRelatedWork W2962980735 @default.
• W2964860107 hasRelatedWork W2963030561 @default.
• W2964860107 hasRelatedWork W2963094593 @default.
• W2964860107 hasRelatedWork W2987639737 @default.
• W2964860107 hasRelatedWork W3034618193 @default.
• W2964860107 hasRelatedWork W3045472490 @default.
• W2964860107 hasRelatedWork W3083405851 @default.
• W2964860107 hasRelatedWork W3098644757 @default.
• W2964860107 hasRelatedWork W3099809348 @default.

• next