Matches in SemOpenAlex for { <https://semopenalex.org/work/W2079656362> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W2079656362 endingPage "54" @default.
- W2079656362 startingPage "39" @default.
- W2079656362 abstract "In this paper, we consider the problem of on-line prediction in which at each time an unlabeled instance is given and then a prediction algorithm outputs a probability distribution over the set of labels rather than {0, 1}-values before it sees the correct label. For this setting, we propose a weighted-average-type on-line stochastic prediction algorithm WA, which can be regarded as a hybrid of the Bayes algorithm and a sequential real-valued parameter estimation method. We derive upper bounds on the instantaneous logarithmic loss and cumulative logarithmic loss for WA in both the example-dependent form and the expected form (the expectation is taken with respect to the fixed target distribution of sequences). Specifically, under some specific parametric assumptions for target rules, we prove that WA is optimal in the sense that the upper bound on the expected cumulative logarithmic loss for WA asymptotically matches Rissanen′s coding-theoretic lower bound. Further, we derive an upper bound on the expected cumulative quadratic loss by making use of relationships between the quadratic loss and the logarithmic loss. Throughout the paper, we relate computational learning theory to information theory, most specifically, Rissanen′s predictive minimum description length principle, by giving noiseless coding theoretic interpretations to the loss bounds." @default.
- W2079656362 created "2016-06-24" @default.
- W2079656362 creator A5021981442 @default.
- W2079656362 date "1995-05-01" @default.
- W2079656362 modified "2023-10-18" @default.
- W2079656362 title "A Loss Bound Model for On-Line Stochastic Prediction Algorithms" @default.
- W2079656362 doi "https://doi.org/10.1006/inco.1995.1076" @default.
- W2079656362 hasPublicationYear "1995" @default.
- W2079656362 type Work @default.
- W2079656362 sameAs 2079656362 @default.
- W2079656362 citedByCount "13" @default.
- W2079656362 countsByYear W20796563622021 @default.
- W2079656362 countsByYear W20796563622023 @default.
- W2079656362 crossrefType "journal-article" @default.
- W2079656362 hasAuthorship W2079656362A5021981442 @default.
- W2079656362 hasBestOaLocation W20796563621 @default.
- W2079656362 hasConcept C105795698 @default.
- W2079656362 hasConcept C107673813 @default.
- W2079656362 hasConcept C11413529 @default.
- W2079656362 hasConcept C117251300 @default.
- W2079656362 hasConcept C126255220 @default.
- W2079656362 hasConcept C129844170 @default.
- W2079656362 hasConcept C134306372 @default.
- W2079656362 hasConcept C198352243 @default.
- W2079656362 hasConcept C207201462 @default.
- W2079656362 hasConcept C2524010 @default.
- W2079656362 hasConcept C28826006 @default.
- W2079656362 hasConcept C33923547 @default.
- W2079656362 hasConcept C39927690 @default.
- W2079656362 hasConcept C55974624 @default.
- W2079656362 hasConcept C77553402 @default.
- W2079656362 hasConcept C87465248 @default.
- W2079656362 hasConceptScore W2079656362C105795698 @default.
- W2079656362 hasConceptScore W2079656362C107673813 @default.
- W2079656362 hasConceptScore W2079656362C11413529 @default.
- W2079656362 hasConceptScore W2079656362C117251300 @default.
- W2079656362 hasConceptScore W2079656362C126255220 @default.
- W2079656362 hasConceptScore W2079656362C129844170 @default.
- W2079656362 hasConceptScore W2079656362C134306372 @default.
- W2079656362 hasConceptScore W2079656362C198352243 @default.
- W2079656362 hasConceptScore W2079656362C207201462 @default.
- W2079656362 hasConceptScore W2079656362C2524010 @default.
- W2079656362 hasConceptScore W2079656362C28826006 @default.
- W2079656362 hasConceptScore W2079656362C33923547 @default.
- W2079656362 hasConceptScore W2079656362C39927690 @default.
- W2079656362 hasConceptScore W2079656362C55974624 @default.
- W2079656362 hasConceptScore W2079656362C77553402 @default.
- W2079656362 hasConceptScore W2079656362C87465248 @default.
- W2079656362 hasIssue "1" @default.
- W2079656362 hasLocation W20796563621 @default.
- W2079656362 hasOpenAccess W2079656362 @default.
- W2079656362 hasPrimaryLocation W20796563621 @default.
- W2079656362 hasRelatedWork W1516206434 @default.
- W2079656362 hasRelatedWork W2012452884 @default.
- W2079656362 hasRelatedWork W2079656362 @default.
- W2079656362 hasRelatedWork W2083129711 @default.
- W2079656362 hasRelatedWork W2089630933 @default.
- W2079656362 hasRelatedWork W2347501195 @default.
- W2079656362 hasRelatedWork W2355832510 @default.
- W2079656362 hasRelatedWork W2783443175 @default.
- W2079656362 hasRelatedWork W3104458475 @default.
- W2079656362 hasRelatedWork W3123919776 @default.
- W2079656362 hasVolume "119" @default.
- W2079656362 isParatext "false" @default.
- W2079656362 isRetracted "false" @default.
- W2079656362 magId "2079656362" @default.
- W2079656362 workType "article" @default.