Matches in SemOpenAlex for { <https://semopenalex.org/work/W2100483486> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W2100483486 endingPage "37" @default.
- W2100483486 startingPage "21" @default.
- W2100483486 abstract "We study online regret minimization algorithms in an experts setting. In this setting, the algorithm chooses a distribution over experts at each time step and receives a gain that is a weighted average of the experts’ instantaneous gains. We consider a bicriteria setting, examining not only the standard notion of regret to the best expert, but also the regret to the average of all experts, the regret to any given fixed mixture of experts, or the regret to the worst expert. This study leads both to new understanding of the limitations of existing no-regret algorithms, and to new algorithms with novel performance guarantees. More specifically, we show that any algorithm that achieves only $O(sqrt{T})$ cumulative regret to the best expert on a sequence of T trials must, in the worst case, suffer regret $varOmega(sqrt{T})$ to the average, and that for a wide class of update rules that includes many existing no-regret algorithms (such as Exponential Weights and Follow the Perturbed Leader), the product of the regret to the best and the regret to the average is, in the worst case, Ω(T). We then describe and analyze two alternate new algorithms that both achieve cumulative regret only $O(sqrt{T}log T)$ to the best expert and have only constant regret to any given fixed distribution over experts (that is, with no dependence on either T or the number of experts N). The key to the first algorithm is the gradual increase in the “aggressiveness” of updates in response to observed divergences in expert performances. The second algorithm is a simple twist on standard exponential-update algorithms." @default.
- W2100483486 created "2016-06-24" @default.
- W2100483486 creator A5014637159 @default.
- W2100483486 creator A5022460492 @default.
- W2100483486 creator A5029730907 @default.
- W2100483486 creator A5071856218 @default.
- W2100483486 date "2008-05-13" @default.
- W2100483486 modified "2023-09-27" @default.
- W2100483486 title "Regret to the best vs. regret to the average" @default.
- W2100483486 cites W1570963478 @default.
- W2100483486 cites W1964964840 @default.
- W2100483486 cites W2005951230 @default.
- W2100483486 cites W2055639053 @default.
- W2100483486 cites W2065368202 @default.
- W2100483486 cites W2093825590 @default.
- W2100483486 cites W2169401877 @default.
- W2100483486 cites W3149261725 @default.
- W2100483486 cites W4237883889 @default.
- W2100483486 doi "https://doi.org/10.1007/s10994-008-5060-z" @default.
- W2100483486 hasPublicationYear "2008" @default.
- W2100483486 type Work @default.
- W2100483486 sameAs 2100483486 @default.
- W2100483486 citedByCount "27" @default.
- W2100483486 countsByYear W21004834862012 @default.
- W2100483486 countsByYear W21004834862013 @default.
- W2100483486 countsByYear W21004834862014 @default.
- W2100483486 countsByYear W21004834862015 @default.
- W2100483486 countsByYear W21004834862016 @default.
- W2100483486 countsByYear W21004834862018 @default.
- W2100483486 countsByYear W21004834862019 @default.
- W2100483486 countsByYear W21004834862020 @default.
- W2100483486 countsByYear W21004834862021 @default.
- W2100483486 countsByYear W21004834862022 @default.
- W2100483486 crossrefType "journal-article" @default.
- W2100483486 hasAuthorship W2100483486A5014637159 @default.
- W2100483486 hasAuthorship W2100483486A5022460492 @default.
- W2100483486 hasAuthorship W2100483486A5029730907 @default.
- W2100483486 hasAuthorship W2100483486A5071856218 @default.
- W2100483486 hasBestOaLocation W21004834861 @default.
- W2100483486 hasConcept C105795698 @default.
- W2100483486 hasConcept C126255220 @default.
- W2100483486 hasConcept C134306372 @default.
- W2100483486 hasConcept C151376022 @default.
- W2100483486 hasConcept C33923547 @default.
- W2100483486 hasConcept C41008148 @default.
- W2100483486 hasConcept C50817715 @default.
- W2100483486 hasConceptScore W2100483486C105795698 @default.
- W2100483486 hasConceptScore W2100483486C126255220 @default.
- W2100483486 hasConceptScore W2100483486C134306372 @default.
- W2100483486 hasConceptScore W2100483486C151376022 @default.
- W2100483486 hasConceptScore W2100483486C33923547 @default.
- W2100483486 hasConceptScore W2100483486C41008148 @default.
- W2100483486 hasConceptScore W2100483486C50817715 @default.
- W2100483486 hasIssue "1-2" @default.
- W2100483486 hasLocation W21004834861 @default.
- W2100483486 hasLocation W21004834862 @default.
- W2100483486 hasOpenAccess W2100483486 @default.
- W2100483486 hasPrimaryLocation W21004834861 @default.
- W2100483486 hasRelatedWork W1954007105 @default.
- W2100483486 hasRelatedWork W2046840684 @default.
- W2100483486 hasRelatedWork W2128751223 @default.
- W2100483486 hasRelatedWork W2301027479 @default.
- W2100483486 hasRelatedWork W2742141334 @default.
- W2100483486 hasRelatedWork W3111617249 @default.
- W2100483486 hasRelatedWork W3159392088 @default.
- W2100483486 hasRelatedWork W3176362036 @default.
- W2100483486 hasRelatedWork W4287555357 @default.
- W2100483486 hasRelatedWork W4287634665 @default.
- W2100483486 hasVolume "72" @default.
- W2100483486 isParatext "false" @default.
- W2100483486 isRetracted "false" @default.
- W2100483486 magId "2100483486" @default.
- W2100483486 workType "article" @default.