FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2156291289> ?p ?o ?g. }

• W2156291289 endingPage "1793" @default.
• W2156291289 startingPage "1782" @default.
• W2156291289 abstract "Recently much work has been done analyzing online machine learning algorithms in a worst case setting, where no probabilistic assumptions are made about the data. This is analogous to the H/sup /spl infin// setting used in adaptive linear filtering. Bregman divergences have become a standard tool for analyzing online machine learning algorithms. Using these divergences, we motivate a generalization of the least mean squared (LMS) algorithm. The loss bounds for these so-called p-norm algorithms involve other norms than the standard 2-norm. The bounds can be significantly better if a large proportion of the input variables are irrelevant, i.e., if the weight vector we are trying to learn is sparse. We also prove results for nonstationary targets. We only know how to apply kernel methods to the standard LMS algorithm (i.e., p=2). However, even in the general p-norm case, we can handle generalized linear models where the output of the system is a linear function combined with a nonlinear transfer function (e.g., the logistic sigmoid)." @default.
• W2156291289 created "2016-06-24" @default.
• W2156291289 creator A5002430773 @default.
• W2156291289 creator A5024345056 @default.
• W2156291289 creator A5079068357 @default.
• W2156291289 date "2006-05-01" @default.
• W2156291289 modified "2023-10-18" @default.
• W2156291289 title "The p-norm generalization of the LMS algorithm for adaptive filtering" @default.
• W2156291289 cites W1506313179 @default.
• W2156291289 cites W1540198634 @default.
• W2156291289 cites W1553032475 @default.
• W2156291289 cites W1724735345 @default.
• W2156291289 cites W1952987489 @default.
• W2156291289 cites W1968444040 @default.
• W2156291289 cites W1976578332 @default.
• W2156291289 cites W2033468335 @default.
• W2156291289 cites W2041954531 @default.
• W2156291289 cites W2055639053 @default.
• W2156291289 cites W2069317438 @default.
• W2156291289 cites W2087614174 @default.
• W2156291289 cites W2102800374 @default.
• W2156291289 cites W2103589858 @default.
• W2156291289 cites W2109339818 @default.
• W2156291289 cites W2141996170 @default.
• W2156291289 cites W2156291289 @default.
• W2156291289 cites W3023115439 @default.
• W2156291289 cites W3106162655 @default.
• W2156291289 cites W4246994868 @default.
• W2156291289 doi "https://doi.org/10.1109/tsp.2006.872551" @default.
• W2156291289 hasPublicationYear "2006" @default.
• W2156291289 type Work @default.
• W2156291289 sameAs 2156291289 @default.
• W2156291289 citedByCount "63" @default.
• W2156291289 countsByYear W21562912892012 @default.
• W2156291289 countsByYear W21562912892013 @default.
• W2156291289 countsByYear W21562912892014 @default.
• W2156291289 countsByYear W21562912892015 @default.
• W2156291289 countsByYear W21562912892016 @default.
• W2156291289 countsByYear W21562912892017 @default.
• W2156291289 countsByYear W21562912892018 @default.
• W2156291289 countsByYear W21562912892019 @default.
• W2156291289 countsByYear W21562912892020 @default.
• W2156291289 countsByYear W21562912892021 @default.
• W2156291289 countsByYear W21562912892022 @default.
• W2156291289 countsByYear W21562912892023 @default.
• W2156291289 crossrefType "journal-article" @default.
• W2156291289 hasAuthorship W2156291289A5002430773 @default.
• W2156291289 hasAuthorship W2156291289A5024345056 @default.
• W2156291289 hasAuthorship W2156291289A5079068357 @default.
• W2156291289 hasBestOaLocation W21562912892 @default.
• W2156291289 hasConcept C102248274 @default.
• W2156291289 hasConcept C105795698 @default.
• W2156291289 hasConcept C11413529 @default.
• W2156291289 hasConcept C134306372 @default.
• W2156291289 hasConcept C154945302 @default.
• W2156291289 hasConcept C177148314 @default.
• W2156291289 hasConcept C17744445 @default.
• W2156291289 hasConcept C191795146 @default.
• W2156291289 hasConcept C199539241 @default.
• W2156291289 hasConcept C32617633 @default.
• W2156291289 hasConcept C33923547 @default.
• W2156291289 hasConcept C41008148 @default.
• W2156291289 hasConcept C49937458 @default.
• W2156291289 hasConcept C50644808 @default.
• W2156291289 hasConcept C81388566 @default.
• W2156291289 hasConceptScore W2156291289C102248274 @default.
• W2156291289 hasConceptScore W2156291289C105795698 @default.
• W2156291289 hasConceptScore W2156291289C11413529 @default.
• W2156291289 hasConceptScore W2156291289C134306372 @default.
• W2156291289 hasConceptScore W2156291289C154945302 @default.
• W2156291289 hasConceptScore W2156291289C177148314 @default.
• W2156291289 hasConceptScore W2156291289C17744445 @default.
• W2156291289 hasConceptScore W2156291289C191795146 @default.
• W2156291289 hasConceptScore W2156291289C199539241 @default.
• W2156291289 hasConceptScore W2156291289C32617633 @default.
• W2156291289 hasConceptScore W2156291289C33923547 @default.
• W2156291289 hasConceptScore W2156291289C41008148 @default.
• W2156291289 hasConceptScore W2156291289C49937458 @default.
• W2156291289 hasConceptScore W2156291289C50644808 @default.
• W2156291289 hasConceptScore W2156291289C81388566 @default.
• W2156291289 hasIssue "5" @default.
• W2156291289 hasLocation W21562912891 @default.
• W2156291289 hasLocation W21562912892 @default.
• W2156291289 hasLocation W21562912893 @default.
• W2156291289 hasOpenAccess W2156291289 @default.
• W2156291289 hasPrimaryLocation W21562912891 @default.
• W2156291289 hasRelatedWork W2051390178 @default.
• W2156291289 hasRelatedWork W2081010624 @default.
• W2156291289 hasRelatedWork W2081837274 @default.
• W2156291289 hasRelatedWork W2138121076 @default.
• W2156291289 hasRelatedWork W2153218171 @default.
• W2156291289 hasRelatedWork W2253481662 @default.
• W2156291289 hasRelatedWork W2287235845 @default.
• W2156291289 hasRelatedWork W2357454918 @default.
• W2156291289 hasRelatedWork W2386759935 @default.
• W2156291289 hasRelatedWork W2586228848 @default.
• W2156291289 hasVolume "54" @default.
• W2156291289 isParatext "false" @default.

• next