FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2116772053> ?p ?o ?g. }

• W2116772053 endingPage "2934" @default.
• W2116772053 startingPage "2901" @default.
• W2116772053 abstract "We introduce new Perceptron-based algorithms for the online multitask binary classification problem. Under suitable regularity conditions, our algorithms are shown to improve on their baselines by a factor proportional to the number of tasks. We achieve these improvements using various types of regularization that bias our algorithms towards specific notions of task relatedness. More specifically, similarity among tasks is either measured in terms of the geometric closeness of the task reference vectors or as a function of the dimension of their spanned subspace. In addition to adapting to the online setting a mix of known techniques, such as the multitask kernels of Evgeniou et al., our analysis also introduces a matrix-based multitask extension of the p-norm Perceptron, which is used to implement spectral co-regularization. Experiments on real-world data sets complement and support our theoretical findings." @default.
• W2116772053 created "2016-06-24" @default.
• W2116772053 creator A5024358077 @default.
• W2116772053 creator A5074621968 @default.
• W2116772053 creator A5091448045 @default.
• W2116772053 date "2010-03-01" @default.
• W2116772053 modified "2023-09-28" @default.
• W2116772053 title "Linear Algorithms for Online Multitask Classification" @default.
• W2116772053 cites W1484446963 @default.
• W2116772053 cites W1488435683 @default.
• W2116772053 cites W1505731132 @default.
• W2116772053 cites W1506313179 @default.
• W2116772053 cites W1506895146 @default.
• W2116772053 cites W1536675765 @default.
• W2116772053 cites W1537145174 @default.
• W2116772053 cites W1540198634 @default.
• W2116772053 cites W1540586255 @default.
• W2116772053 cites W1548525349 @default.
• W2116772053 cites W1560143607 @default.
• W2116772053 cites W1570963478 @default.
• W2116772053 cites W1575259140 @default.
• W2116772053 cites W1590313574 @default.
• W2116772053 cites W1786935204 @default.
• W2116772053 cites W1939941161 @default.
• W2116772053 cites W1979711143 @default.
• W2116772053 cites W1993793464 @default.
• W2116772053 cites W2012715465 @default.
• W2116772053 cites W2016070790 @default.
• W2116772053 cites W2016384870 @default.
• W2116772053 cites W2065861851 @default.
• W2116772053 cites W2102800374 @default.
• W2116772053 cites W2103024562 @default.
• W2116772053 cites W2110652811 @default.
• W2116772053 cites W2130903752 @default.
• W2116772053 cites W2133348086 @default.
• W2116772053 cites W2140676093 @default.
• W2116772053 cites W2144752499 @default.
• W2116772053 cites W2145134605 @default.
• W2116772053 cites W2149934276 @default.
• W2116772053 cites W2156267734 @default.
• W2116772053 cites W2162667926 @default.
• W2116772053 cites W2165644552 @default.
• W2116772053 cites W2170563643 @default.
• W2116772053 cites W2293569770 @default.
• W2116772053 cites W2610857016 @default.
• W2116772053 cites W2797638056 @default.
• W2116772053 cites W3124254895 @default.
• W2116772053 hasPublicationYear "2010" @default.
• W2116772053 type Work @default.
• W2116772053 sameAs 2116772053 @default.
• W2116772053 citedByCount "59" @default.
• W2116772053 countsByYear W21167720532012 @default.
• W2116772053 countsByYear W21167720532013 @default.
• W2116772053 countsByYear W21167720532014 @default.
• W2116772053 countsByYear W21167720532015 @default.
• W2116772053 countsByYear W21167720532016 @default.
• W2116772053 countsByYear W21167720532017 @default.
• W2116772053 countsByYear W21167720532018 @default.
• W2116772053 countsByYear W21167720532019 @default.
• W2116772053 countsByYear W21167720532020 @default.
• W2116772053 countsByYear W21167720532021 @default.
• W2116772053 crossrefType "journal-article" @default.
• W2116772053 hasAuthorship W2116772053A5024358077 @default.
• W2116772053 hasAuthorship W2116772053A5074621968 @default.
• W2116772053 hasAuthorship W2116772053A5091448045 @default.
• W2116772053 hasConcept C104317684 @default.
• W2116772053 hasConcept C112313634 @default.
• W2116772053 hasConcept C11413529 @default.
• W2116772053 hasConcept C119857082 @default.
• W2116772053 hasConcept C12267149 @default.
• W2116772053 hasConcept C127716648 @default.
• W2116772053 hasConcept C134306372 @default.
• W2116772053 hasConcept C154945302 @default.
• W2116772053 hasConcept C162324750 @default.
• W2116772053 hasConcept C185592680 @default.
• W2116772053 hasConcept C187736073 @default.
• W2116772053 hasConcept C188082640 @default.
• W2116772053 hasConcept C2776135515 @default.
• W2116772053 hasConcept C2779545769 @default.
• W2116772053 hasConcept C2780451532 @default.
• W2116772053 hasConcept C28006648 @default.
• W2116772053 hasConcept C32834561 @default.
• W2116772053 hasConcept C33923547 @default.
• W2116772053 hasConcept C41008148 @default.
• W2116772053 hasConcept C50644808 @default.
• W2116772053 hasConcept C55493867 @default.
• W2116772053 hasConcept C60908668 @default.
• W2116772053 hasConcept C66905080 @default.
• W2116772053 hasConceptScore W2116772053C104317684 @default.
• W2116772053 hasConceptScore W2116772053C112313634 @default.
• W2116772053 hasConceptScore W2116772053C11413529 @default.
• W2116772053 hasConceptScore W2116772053C119857082 @default.
• W2116772053 hasConceptScore W2116772053C12267149 @default.
• W2116772053 hasConceptScore W2116772053C127716648 @default.
• W2116772053 hasConceptScore W2116772053C134306372 @default.
• W2116772053 hasConceptScore W2116772053C154945302 @default.
• W2116772053 hasConceptScore W2116772053C162324750 @default.
• W2116772053 hasConceptScore W2116772053C185592680 @default.

• next