Matches in SemOpenAlex for { <https://semopenalex.org/work/W2963753225> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2963753225 endingPage "1498" @default.
- W2963753225 startingPage "1489" @default.
- W2963753225 abstract "The dueling bandit is a learning framework where the feedback information in the learning process is restricted to noisy comparison between a pair of actions. In this paper, we address a dueling bandit problem based on a cost function over a continuous space. We propose a stochastic mirror descent algorithm and show that the algorithm achieves an $O(sqrt{Tlog T})$-regret bound under strong convexity and smoothness assumptions for the cost function. Then, we clarify the equivalence between regret minimization in dueling bandit and convex optimization for the cost function. Moreover, considering a lower bound in convex optimization, it is turned out that our algorithm achieves the optimal convergence rate in convex optimization and the optimal regret in dueling bandit except for a logarithmic factor." @default.
- W2963753225 created "2019-07-30" @default.
- W2963753225 creator A5003820265 @default.
- W2963753225 date "2017-01-01" @default.
- W2963753225 modified "2023-09-24" @default.
- W2963753225 title "Regret Analysis for Continuous Dueling Bandit" @default.
- W2963753225 hasPublicationYear "2017" @default.
- W2963753225 type Work @default.
- W2963753225 sameAs 2963753225 @default.
- W2963753225 citedByCount "2" @default.
- W2963753225 countsByYear W29637532252018 @default.
- W2963753225 countsByYear W29637532252019 @default.
- W2963753225 crossrefType "proceedings-article" @default.
- W2963753225 hasAuthorship W2963753225A5003820265 @default.
- W2963753225 hasConcept C102634674 @default.
- W2963753225 hasConcept C106159729 @default.
- W2963753225 hasConcept C112680207 @default.
- W2963753225 hasConcept C118615104 @default.
- W2963753225 hasConcept C119857082 @default.
- W2963753225 hasConcept C123197309 @default.
- W2963753225 hasConcept C126255220 @default.
- W2963753225 hasConcept C134306372 @default.
- W2963753225 hasConcept C14036430 @default.
- W2963753225 hasConcept C145446738 @default.
- W2963753225 hasConcept C157972887 @default.
- W2963753225 hasConcept C162324750 @default.
- W2963753225 hasConcept C2524010 @default.
- W2963753225 hasConcept C2780069185 @default.
- W2963753225 hasConcept C33923547 @default.
- W2963753225 hasConcept C39927690 @default.
- W2963753225 hasConcept C41008148 @default.
- W2963753225 hasConcept C50817715 @default.
- W2963753225 hasConcept C72134830 @default.
- W2963753225 hasConcept C77553402 @default.
- W2963753225 hasConcept C78458016 @default.
- W2963753225 hasConcept C86803240 @default.
- W2963753225 hasConceptScore W2963753225C102634674 @default.
- W2963753225 hasConceptScore W2963753225C106159729 @default.
- W2963753225 hasConceptScore W2963753225C112680207 @default.
- W2963753225 hasConceptScore W2963753225C118615104 @default.
- W2963753225 hasConceptScore W2963753225C119857082 @default.
- W2963753225 hasConceptScore W2963753225C123197309 @default.
- W2963753225 hasConceptScore W2963753225C126255220 @default.
- W2963753225 hasConceptScore W2963753225C134306372 @default.
- W2963753225 hasConceptScore W2963753225C14036430 @default.
- W2963753225 hasConceptScore W2963753225C145446738 @default.
- W2963753225 hasConceptScore W2963753225C157972887 @default.
- W2963753225 hasConceptScore W2963753225C162324750 @default.
- W2963753225 hasConceptScore W2963753225C2524010 @default.
- W2963753225 hasConceptScore W2963753225C2780069185 @default.
- W2963753225 hasConceptScore W2963753225C33923547 @default.
- W2963753225 hasConceptScore W2963753225C39927690 @default.
- W2963753225 hasConceptScore W2963753225C41008148 @default.
- W2963753225 hasConceptScore W2963753225C50817715 @default.
- W2963753225 hasConceptScore W2963753225C72134830 @default.
- W2963753225 hasConceptScore W2963753225C77553402 @default.
- W2963753225 hasConceptScore W2963753225C78458016 @default.
- W2963753225 hasConceptScore W2963753225C86803240 @default.
- W2963753225 hasLocation W29637532251 @default.
- W2963753225 hasOpenAccess W2963753225 @default.
- W2963753225 hasPrimaryLocation W29637532251 @default.
- W2963753225 hasRelatedWork W2152898676 @default.
- W2963753225 hasRelatedWork W2575782769 @default.
- W2963753225 hasRelatedWork W2751157675 @default.
- W2963753225 hasRelatedWork W2751686538 @default.
- W2963753225 hasRelatedWork W2903367700 @default.
- W2963753225 hasRelatedWork W2946909365 @default.
- W2963753225 hasRelatedWork W2951665052 @default.
- W2963753225 hasRelatedWork W2955643364 @default.
- W2963753225 hasRelatedWork W2963350293 @default.
- W2963753225 hasRelatedWork W2990520825 @default.
- W2963753225 hasRelatedWork W3022410481 @default.
- W2963753225 hasRelatedWork W3038622337 @default.
- W2963753225 hasRelatedWork W3104156937 @default.
- W2963753225 hasRelatedWork W3124174978 @default.
- W2963753225 hasRelatedWork W3149052698 @default.
- W2963753225 hasRelatedWork W3158538256 @default.
- W2963753225 hasRelatedWork W3173673246 @default.
- W2963753225 hasRelatedWork W3175554921 @default.
- W2963753225 hasRelatedWork W3213578318 @default.
- W2963753225 hasRelatedWork W2610070984 @default.
- W2963753225 hasVolume "30" @default.
- W2963753225 isParatext "false" @default.
- W2963753225 isRetracted "false" @default.
- W2963753225 magId "2963753225" @default.
- W2963753225 workType "article" @default.