Matches in SemOpenAlex for { <https://semopenalex.org/work/W3044446985> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3044446985 endingPage "4817" @default.
- W3044446985 startingPage "4790" @default.
- W3044446985 abstract "We consider a multi-hypothesis testing problem involving a <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$K$ </tex-math></inline-formula> -armed bandit. Each arm’s signal follows a distribution from a vector exponential family. The actual parameters of the arms are unknown to the decision maker. The decision maker incurs a delay cost for delay until a decision and a switching cost whenever he switches from one arm to another. His goal is to minimise the overall cost until a decision is reached on the true hypothesis. Of interest are policies that satisfy a given constraint on the probability of false detection. This is a sequential decision making problem where the decision maker gets only a limited view of the true state of nature at each stage, but can control his view by choosing the arm to observe at each stage. An information-theoretic lower bound on the total cost (expected time for a reliable decision plus total switching cost) is first identified, and a variation on a sequential policy based on the generalised likelihood ratio statistic is then studied. Due to the vector exponential family assumption, the signal processing at each stage is simple; the associated conjugate prior distribution on the unknown model parameters enables easy updates of the posterior distribution. The proposed policy, with a suitable threshold for stopping, is shown to satisfy the given constraint on the probability of false detection. Under a continuous selection assumption, the policy is also shown to be asymptotically optimal in terms of the total cost among all policies that satisfy the constraint on the probability of false detection." @default.
- W3044446985 created "2020-07-29" @default.
- W3044446985 creator A5011321394 @default.
- W3044446985 creator A5030430086 @default.
- W3044446985 creator A5065705720 @default.
- W3044446985 creator A5072029533 @default.
- W3044446985 date "2022-07-01" @default.
- W3044446985 modified "2023-09-27" @default.
- W3044446985 title "Sequential Multi-Hypothesis Testing in Multi-Armed Bandit Problems: An Approach for Asymptotic Optimality" @default.
- W3044446985 cites W1491720843 @default.
- W3044446985 cites W1910836046 @default.
- W3044446985 cites W2053321475 @default.
- W3044446985 cites W2079120178 @default.
- W3044446985 cites W2109690147 @default.
- W3044446985 cites W2759246051 @default.
- W3044446985 cites W2764044571 @default.
- W3044446985 cites W2918531990 @default.
- W3044446985 cites W2951412892 @default.
- W3044446985 cites W2955202341 @default.
- W3044446985 cites W2962735187 @default.
- W3044446985 cites W2964046421 @default.
- W3044446985 cites W2964198003 @default.
- W3044446985 cites W2975876312 @default.
- W3044446985 cites W3133603318 @default.
- W3044446985 cites W3163486065 @default.
- W3044446985 cites W4232896127 @default.
- W3044446985 cites W4250589301 @default.
- W3044446985 doi "https://doi.org/10.1109/tit.2022.3159600" @default.
- W3044446985 hasPublicationYear "2022" @default.
- W3044446985 type Work @default.
- W3044446985 sameAs 3044446985 @default.
- W3044446985 citedByCount "4" @default.
- W3044446985 countsByYear W30444469852020 @default.
- W3044446985 countsByYear W30444469852021 @default.
- W3044446985 countsByYear W30444469852022 @default.
- W3044446985 countsByYear W30444469852023 @default.
- W3044446985 crossrefType "journal-article" @default.
- W3044446985 hasAuthorship W3044446985A5011321394 @default.
- W3044446985 hasAuthorship W3044446985A5030430086 @default.
- W3044446985 hasAuthorship W3044446985A5065705720 @default.
- W3044446985 hasAuthorship W3044446985A5072029533 @default.
- W3044446985 hasBestOaLocation W30444469852 @default.
- W3044446985 hasConcept C105795698 @default.
- W3044446985 hasConcept C11413529 @default.
- W3044446985 hasConcept C126255220 @default.
- W3044446985 hasConcept C2524010 @default.
- W3044446985 hasConcept C2776036281 @default.
- W3044446985 hasConcept C28901747 @default.
- W3044446985 hasConcept C33923547 @default.
- W3044446985 hasConcept C34602496 @default.
- W3044446985 hasConcept C41008148 @default.
- W3044446985 hasConcept C55974624 @default.
- W3044446985 hasConcept C80478641 @default.
- W3044446985 hasConceptScore W3044446985C105795698 @default.
- W3044446985 hasConceptScore W3044446985C11413529 @default.
- W3044446985 hasConceptScore W3044446985C126255220 @default.
- W3044446985 hasConceptScore W3044446985C2524010 @default.
- W3044446985 hasConceptScore W3044446985C2776036281 @default.
- W3044446985 hasConceptScore W3044446985C28901747 @default.
- W3044446985 hasConceptScore W3044446985C33923547 @default.
- W3044446985 hasConceptScore W3044446985C34602496 @default.
- W3044446985 hasConceptScore W3044446985C41008148 @default.
- W3044446985 hasConceptScore W3044446985C55974624 @default.
- W3044446985 hasConceptScore W3044446985C80478641 @default.
- W3044446985 hasFunder F4320334771 @default.
- W3044446985 hasIssue "7" @default.
- W3044446985 hasLocation W30444469851 @default.
- W3044446985 hasLocation W30444469852 @default.
- W3044446985 hasLocation W30444469853 @default.
- W3044446985 hasOpenAccess W3044446985 @default.
- W3044446985 hasPrimaryLocation W30444469851 @default.
- W3044446985 hasRelatedWork W1963887719 @default.
- W3044446985 hasRelatedWork W2015961697 @default.
- W3044446985 hasRelatedWork W2066652675 @default.
- W3044446985 hasRelatedWork W2107670413 @default.
- W3044446985 hasRelatedWork W2124731500 @default.
- W3044446985 hasRelatedWork W2955202341 @default.
- W3044446985 hasRelatedWork W3044446985 @default.
- W3044446985 hasRelatedWork W3162750348 @default.
- W3044446985 hasRelatedWork W3183426902 @default.
- W3044446985 hasRelatedWork W580630767 @default.
- W3044446985 hasVolume "68" @default.
- W3044446985 isParatext "false" @default.
- W3044446985 isRetracted "false" @default.
- W3044446985 magId "3044446985" @default.
- W3044446985 workType "article" @default.