FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3022720367> ?p ?o ?g. }

• W3022720367 endingPage "1736" @default.
• W3022720367 startingPage "1705" @default.
• W3022720367 abstract "We give an algorithm for the on-line learning of permutations. The algorithm maintains its uncertainty about the target permutation as a doubly stochastic weight matrix, and makes predictions using an efficient method for decomposing the weight matrix into a convex combination of permutations. The weight matrix is updated by multiplying the current matrix entries by exponential factors, and an iterative procedure is needed to restore double stochasticity. Even though the result of this procedure does not have a closed form, a new analysis approach allows us to prove an optimal (up to small constant factors) bound on the regret of our algorithm. This regret bound is significantly better than that of either Kalai and Vempala's more efficient Follow the Perturbed Leader algorithm or the computationally expensive method of explicitly representing each permutation as an expert." @default.
• W3022720367 created "2020-05-13" @default.
• W3022720367 creator A5014740431 @default.
• W3022720367 creator A5079068357 @default.
• W3022720367 date "2009-12-01" @default.
• W3022720367 modified "2023-10-06" @default.
• W3022720367 title "Learning Permutations with Exponential Weights" @default.
• W3022720367 cites W1495813543 @default.
• W3022720367 cites W1506313179 @default.
• W3022720367 cites W1570963478 @default.
• W3022720367 cites W1598420512 @default.
• W3022720367 cites W1608316568 @default.
• W3022720367 cites W1628829797 @default.
• W3022720367 cites W1724735345 @default.
• W3022720367 cites W1970041563 @default.
• W3022720367 cites W1979675141 @default.
• W3022720367 cites W1984958640 @default.
• W3022720367 cites W1988790447 @default.
• W3022720367 cites W1990283121 @default.
• W3022720367 cites W2010997912 @default.
• W3022720367 cites W2033468335 @default.
• W3022720367 cites W2034025033 @default.
• W3022720367 cites W2059774588 @default.
• W3022720367 cites W2069317438 @default.
• W3022720367 cites W2077902449 @default.
• W3022720367 cites W2093825590 @default.
• W3022720367 cites W2099811697 @default.
• W3022720367 cites W2103589858 @default.
• W3022720367 cites W2115193820 @default.
• W3022720367 cites W2119883797 @default.
• W3022720367 cites W2123959253 @default.
• W3022720367 cites W2131867500 @default.
• W3022720367 cites W2141996170 @default.
• W3022720367 cites W2150864256 @default.
• W3022720367 cites W2161611531 @default.
• W3022720367 cites W2169401877 @default.
• W3022720367 cites W2333315597 @default.
• W3022720367 cites W2610680804 @default.
• W3022720367 cites W2611627047 @default.
• W3022720367 cites W2798707604 @default.
• W3022720367 cites W3023115439 @default.
• W3022720367 cites W3137830407 @default.
• W3022720367 cites W3396763 @default.
• W3022720367 doi "https://doi.org/10.5555/1577069.1755841" @default.
• W3022720367 hasPublicationYear "2009" @default.
• W3022720367 type Work @default.
• W3022720367 sameAs 3022720367 @default.
• W3022720367 citedByCount "62" @default.
• W3022720367 countsByYear W30227203672012 @default.
• W3022720367 countsByYear W30227203672013 @default.
• W3022720367 countsByYear W30227203672014 @default.
• W3022720367 countsByYear W30227203672015 @default.
• W3022720367 countsByYear W30227203672016 @default.
• W3022720367 countsByYear W30227203672017 @default.
• W3022720367 countsByYear W30227203672018 @default.
• W3022720367 countsByYear W30227203672019 @default.
• W3022720367 countsByYear W30227203672020 @default.
• W3022720367 countsByYear W30227203672021 @default.
• W3022720367 crossrefType "journal-article" @default.
• W3022720367 hasAuthorship W3022720367A5014740431 @default.
• W3022720367 hasAuthorship W3022720367A5079068357 @default.
• W3022720367 hasConcept C105795698 @default.
• W3022720367 hasConcept C106487976 @default.
• W3022720367 hasConcept C112680207 @default.
• W3022720367 hasConcept C11413529 @default.
• W3022720367 hasConcept C114614502 @default.
• W3022720367 hasConcept C115973184 @default.
• W3022720367 hasConcept C121332964 @default.
• W3022720367 hasConcept C126255220 @default.
• W3022720367 hasConcept C134306372 @default.
• W3022720367 hasConcept C151376022 @default.
• W3022720367 hasConcept C159985019 @default.
• W3022720367 hasConcept C192562407 @default.
• W3022720367 hasConcept C199360897 @default.
• W3022720367 hasConcept C21308566 @default.
• W3022720367 hasConcept C24890656 @default.
• W3022720367 hasConcept C2524010 @default.
• W3022720367 hasConcept C2777027219 @default.
• W3022720367 hasConcept C33923547 @default.
• W3022720367 hasConcept C41008148 @default.
• W3022720367 hasConcept C50817715 @default.
• W3022720367 hasConcept C77553402 @default.
• W3022720367 hasConcept C84140500 @default.
• W3022720367 hasConceptScore W3022720367C105795698 @default.
• W3022720367 hasConceptScore W3022720367C106487976 @default.
• W3022720367 hasConceptScore W3022720367C112680207 @default.
• W3022720367 hasConceptScore W3022720367C11413529 @default.
• W3022720367 hasConceptScore W3022720367C114614502 @default.
• W3022720367 hasConceptScore W3022720367C115973184 @default.
• W3022720367 hasConceptScore W3022720367C121332964 @default.
• W3022720367 hasConceptScore W3022720367C126255220 @default.
• W3022720367 hasConceptScore W3022720367C134306372 @default.
• W3022720367 hasConceptScore W3022720367C151376022 @default.
• W3022720367 hasConceptScore W3022720367C159985019 @default.
• W3022720367 hasConceptScore W3022720367C192562407 @default.
• W3022720367 hasConceptScore W3022720367C199360897 @default.
• W3022720367 hasConceptScore W3022720367C21308566 @default.
• W3022720367 hasConceptScore W3022720367C24890656 @default.

• next