Matches in SemOpenAlex for { <https://semopenalex.org/work/W2949279974> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W2949279974 abstract "Is it a good idea to use the frequency of events in the past, as a guide to their frequency in the future (as we all do anyway)? In this paper the question is attacked from the perspective of universal prediction of individual sequences. It is shown that there is a universal sequential probability assignment, such that for a large class loss functions (optimization goals), the predictor minimizing the expected loss under this probability, is a good universal predictor. The proposed probability assignment is based on randomly dithering the empirical frequencies of states in the past, and it is easy to show that randomization is essential. This yields a very simple universal prediction scheme which is similar to Follow-the-Perturbed-Leader (FPL) and works for a large class of loss functions, as well as a partial justification for using probabilistic assumptions." @default.
- W2949279974 created "2019-06-27" @default.
- W2949279974 creator A5062882267 @default.
- W2949279974 creator A5066905280 @default.
- W2949279974 date "2013-01-27" @default.
- W2949279974 modified "2023-09-27" @default.
- W2949279974 title "A Universal Probability Assignment for Prediction of Individual Sequences" @default.
- W2949279974 cites W2099111195 @default.
- W2949279974 cites W2102426343 @default.
- W2949279974 cites W2104334863 @default.
- W2949279974 cites W2211362994 @default.
- W2949279974 cites W2751862591 @default.
- W2949279974 cites W3083047178 @default.
- W2949279974 cites W569528099 @default.
- W2949279974 cites W2154518298 @default.
- W2949279974 cites W2183165793 @default.
- W2949279974 hasPublicationYear "2013" @default.
- W2949279974 type Work @default.
- W2949279974 sameAs 2949279974 @default.
- W2949279974 citedByCount "0" @default.
- W2949279974 crossrefType "posted-content" @default.
- W2949279974 hasAuthorship W2949279974A5062882267 @default.
- W2949279974 hasAuthorship W2949279974A5066905280 @default.
- W2949279974 hasConcept C111472728 @default.
- W2949279974 hasConcept C11413529 @default.
- W2949279974 hasConcept C118615104 @default.
- W2949279974 hasConcept C126255220 @default.
- W2949279974 hasConcept C12713177 @default.
- W2949279974 hasConcept C138885662 @default.
- W2949279974 hasConcept C154945302 @default.
- W2949279974 hasConcept C2777212361 @default.
- W2949279974 hasConcept C2780586882 @default.
- W2949279974 hasConcept C31972630 @default.
- W2949279974 hasConcept C33923547 @default.
- W2949279974 hasConcept C41008148 @default.
- W2949279974 hasConcept C49937458 @default.
- W2949279974 hasConcept C70120467 @default.
- W2949279974 hasConcept C70451592 @default.
- W2949279974 hasConcept C9083635 @default.
- W2949279974 hasConceptScore W2949279974C111472728 @default.
- W2949279974 hasConceptScore W2949279974C11413529 @default.
- W2949279974 hasConceptScore W2949279974C118615104 @default.
- W2949279974 hasConceptScore W2949279974C126255220 @default.
- W2949279974 hasConceptScore W2949279974C12713177 @default.
- W2949279974 hasConceptScore W2949279974C138885662 @default.
- W2949279974 hasConceptScore W2949279974C154945302 @default.
- W2949279974 hasConceptScore W2949279974C2777212361 @default.
- W2949279974 hasConceptScore W2949279974C2780586882 @default.
- W2949279974 hasConceptScore W2949279974C31972630 @default.
- W2949279974 hasConceptScore W2949279974C33923547 @default.
- W2949279974 hasConceptScore W2949279974C41008148 @default.
- W2949279974 hasConceptScore W2949279974C49937458 @default.
- W2949279974 hasConceptScore W2949279974C70120467 @default.
- W2949279974 hasConceptScore W2949279974C70451592 @default.
- W2949279974 hasConceptScore W2949279974C9083635 @default.
- W2949279974 hasLocation W29492799741 @default.
- W2949279974 hasOpenAccess W2949279974 @default.
- W2949279974 hasPrimaryLocation W29492799741 @default.
- W2949279974 hasRelatedWork W1564684328 @default.
- W2949279974 hasRelatedWork W1635409103 @default.
- W2949279974 hasRelatedWork W2004168586 @default.
- W2949279974 hasRelatedWork W2135754715 @default.
- W2949279974 hasRelatedWork W2156005874 @default.
- W2949279974 hasRelatedWork W2161657418 @default.
- W2949279974 hasRelatedWork W2171349590 @default.
- W2949279974 hasRelatedWork W2431918662 @default.
- W2949279974 hasRelatedWork W2521821750 @default.
- W2949279974 hasRelatedWork W2742781314 @default.
- W2949279974 hasRelatedWork W2803642127 @default.
- W2949279974 hasRelatedWork W2890823225 @default.
- W2949279974 hasRelatedWork W2950988985 @default.
- W2949279974 hasRelatedWork W2951243569 @default.
- W2949279974 hasRelatedWork W2952680276 @default.
- W2949279974 hasRelatedWork W2963767011 @default.
- W2949279974 hasRelatedWork W3028888589 @default.
- W2949279974 hasRelatedWork W3033781806 @default.
- W2949279974 hasRelatedWork W811226091 @default.
- W2949279974 hasRelatedWork W73426805 @default.
- W2949279974 isParatext "false" @default.
- W2949279974 isRetracted "false" @default.
- W2949279974 magId "2949279974" @default.
- W2949279974 workType "article" @default.