Matches in SemOpenAlex for { <https://semopenalex.org/work/W2105154442> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2105154442 endingPage "1439" @default.
- W2105154442 startingPage "1424" @default.
- W2105154442 abstract "Rissanen (1978) has introduced stochastic complexity to define the amount of information in a given data sequence relative to a given hypothesis class of probability densities, where the information is measured in terms of the logarithmic loss associated with universal data compression. This paper introduces the notion of extended stochastic complexity (ESC) and demonstrates its effectiveness in design and analysis of learning algorithms in on-line prediction and batch-learning scenarios. ESC can be thought of as an extension of Rissanen's stochastic complexity to the decision-theoretic setting where a general real-valued function is used as a hypothesis and a general loss function is used as a distortion measure. As an application of ESC to on-line prediction, this paper shows that a sequential realization of ESC produces an on-line prediction algorithm called Vovk's aggregating strategy, which can be thought of as an extension of the Bayes algorithm. We derive upper bounds on the cumulative loss for the aggregating strategy both of an expected form and a worst case form in the case where the hypothesis class is continuous. As an application of ESC to batch-learning, this paper shows that a batch-approximation of ESC induces a batch-learning algorithm called the minimum L-complexity algorithm (MLC), which is an extension of the minimum description length (MDL) principle. We derive upper bounds on the statistical risk for the MLC, which are the least to date. Through the ESC we give a unifying view of the most effective learning algorithms that have been explored in computational learning theory." @default.
- W2105154442 created "2016-06-24" @default.
- W2105154442 creator A5021981442 @default.
- W2105154442 date "1998-07-01" @default.
- W2105154442 modified "2023-10-18" @default.
- W2105154442 title "A decision-theoretic extension of stochastic complexity and its applications to learning" @default.
- W2105154442 cites W1483114294 @default.
- W2105154442 cites W1540226724 @default.
- W2105154442 cites W1968908999 @default.
- W2105154442 cites W1974892965 @default.
- W2105154442 cites W1988520084 @default.
- W2105154442 cites W1995875735 @default.
- W2105154442 cites W2009207556 @default.
- W2105154442 cites W2047837509 @default.
- W2105154442 cites W2050660892 @default.
- W2105154442 cites W2054658115 @default.
- W2105154442 cites W2054716087 @default.
- W2105154442 cites W2068782468 @default.
- W2105154442 cites W2079656362 @default.
- W2105154442 cites W2082967074 @default.
- W2105154442 cites W2084544490 @default.
- W2105154442 cites W2095734615 @default.
- W2105154442 cites W2124641450 @default.
- W2105154442 cites W2132119275 @default.
- W2105154442 cites W2160570986 @default.
- W2105154442 cites W4235825416 @default.
- W2105154442 cites W4248175720 @default.
- W2105154442 cites W4254257531 @default.
- W2105154442 doi "https://doi.org/10.1109/18.681319" @default.
- W2105154442 hasPublicationYear "1998" @default.
- W2105154442 type Work @default.
- W2105154442 sameAs 2105154442 @default.
- W2105154442 citedByCount "88" @default.
- W2105154442 countsByYear W21051544422012 @default.
- W2105154442 countsByYear W21051544422013 @default.
- W2105154442 countsByYear W21051544422016 @default.
- W2105154442 countsByYear W21051544422017 @default.
- W2105154442 countsByYear W21051544422018 @default.
- W2105154442 countsByYear W21051544422019 @default.
- W2105154442 countsByYear W21051544422021 @default.
- W2105154442 countsByYear W21051544422023 @default.
- W2105154442 crossrefType "journal-article" @default.
- W2105154442 hasAuthorship W2105154442A5021981442 @default.
- W2105154442 hasConcept C105795698 @default.
- W2105154442 hasConcept C11413529 @default.
- W2105154442 hasConcept C124101348 @default.
- W2105154442 hasConcept C134306372 @default.
- W2105154442 hasConcept C14036430 @default.
- W2105154442 hasConcept C199360897 @default.
- W2105154442 hasConcept C2778029271 @default.
- W2105154442 hasConcept C2780009758 @default.
- W2105154442 hasConcept C2781089630 @default.
- W2105154442 hasConcept C33923547 @default.
- W2105154442 hasConcept C39927690 @default.
- W2105154442 hasConcept C41008148 @default.
- W2105154442 hasConcept C77553402 @default.
- W2105154442 hasConcept C78458016 @default.
- W2105154442 hasConcept C86803240 @default.
- W2105154442 hasConcept C87465248 @default.
- W2105154442 hasConceptScore W2105154442C105795698 @default.
- W2105154442 hasConceptScore W2105154442C11413529 @default.
- W2105154442 hasConceptScore W2105154442C124101348 @default.
- W2105154442 hasConceptScore W2105154442C134306372 @default.
- W2105154442 hasConceptScore W2105154442C14036430 @default.
- W2105154442 hasConceptScore W2105154442C199360897 @default.
- W2105154442 hasConceptScore W2105154442C2778029271 @default.
- W2105154442 hasConceptScore W2105154442C2780009758 @default.
- W2105154442 hasConceptScore W2105154442C2781089630 @default.
- W2105154442 hasConceptScore W2105154442C33923547 @default.
- W2105154442 hasConceptScore W2105154442C39927690 @default.
- W2105154442 hasConceptScore W2105154442C41008148 @default.
- W2105154442 hasConceptScore W2105154442C77553402 @default.
- W2105154442 hasConceptScore W2105154442C78458016 @default.
- W2105154442 hasConceptScore W2105154442C86803240 @default.
- W2105154442 hasConceptScore W2105154442C87465248 @default.
- W2105154442 hasIssue "4" @default.
- W2105154442 hasLocation W21051544421 @default.
- W2105154442 hasOpenAccess W2105154442 @default.
- W2105154442 hasPrimaryLocation W21051544421 @default.
- W2105154442 hasRelatedWork W1982572960 @default.
- W2105154442 hasRelatedWork W2069998960 @default.
- W2105154442 hasRelatedWork W2079656362 @default.
- W2105154442 hasRelatedWork W2163330118 @default.
- W2105154442 hasRelatedWork W2334791747 @default.
- W2105154442 hasRelatedWork W2352495365 @default.
- W2105154442 hasRelatedWork W2389551393 @default.
- W2105154442 hasRelatedWork W3166409534 @default.
- W2105154442 hasRelatedWork W4229773585 @default.
- W2105154442 hasRelatedWork W4251067554 @default.
- W2105154442 hasVolume "44" @default.
- W2105154442 isParatext "false" @default.
- W2105154442 isRetracted "false" @default.
- W2105154442 magId "2105154442" @default.
- W2105154442 workType "article" @default.