FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2920218480> ?p ?o ?g. }

• W2920218480 abstract "We consider decentralized online supervised learning where estimators are chosen from a reproducing kernel Hilbert space (RKHS). Here a multi-agent network aims to learn nonlinear statistical models that are optimal in terms of a global convex functional that aggregates data across the network, while only having access to locally observed streaming data. We address this problem by allowing each agent to learn a local copy of the global regression function while enforcing consensus constraints. We use a penalized variant of functional stochastic gradient descent operating simultaneously with low-dimensional subspace projections. The resulting algorithm allows each individual agent to learn, based upon its locally observed data stream and message passing with its neighbors, a function that is provably close to globally optimal and satisfies the consensus constraints. Moreover, the complexity of the learned regression functions is guaranteed to be finite. We then validate this approach on the Brodatz textures dataset for the case of decentralized online multi-class kernel logistic regression." @default.
• W2920218480 created "2019-03-11" @default.
• W2920218480 creator A5001418995 @default.
• W2920218480 creator A5009808175 @default.
• W2920218480 creator A5021418299 @default.
• W2920218480 creator A5025896653 @default.
• W2920218480 date "2018-10-01" @default.
• W2920218480 modified "2023-09-30" @default.
• W2920218480 title "Decentralized Online Nonparametric Learning" @default.
• W2920218480 cites W1484228140 @default.
• W2920218480 cites W1492832050 @default.
• W2920218480 cites W1503398984 @default.
• W2920218480 cites W1515878031 @default.
• W2920218480 cites W1540155273 @default.
• W2920218480 cites W1542886316 @default.
• W2920218480 cites W1643746074 @default.
• W2920218480 cites W1657655960 @default.
• W2920218480 cites W1994616650 @default.
• W2920218480 cites W2015904350 @default.
• W2920218480 cites W2020909452 @default.
• W2920218480 cites W2031586513 @default.
• W2920218480 cites W2033855314 @default.
• W2920218480 cites W2036760242 @default.
• W2920218480 cites W2043182541 @default.
• W2920218480 cites W2047214985 @default.
• W2920218480 cites W2066332749 @default.
• W2920218480 cites W2078899824 @default.
• W2920218480 cites W2103736488 @default.
• W2920218480 cites W2110652811 @default.
• W2920218480 cites W2116680122 @default.
• W2920218480 cites W2124776405 @default.
• W2920218480 cites W2128659236 @default.
• W2920218480 cites W2139320579 @default.
• W2920218480 cites W2142184324 @default.
• W2920218480 cites W2150621701 @default.
• W2920218480 cites W2153290280 @default.
• W2920218480 cites W2155973058 @default.
• W2920218480 cites W2163112044 @default.
• W2920218480 cites W2163605009 @default.
• W2920218480 cites W2272205360 @default.
• W2920218480 cites W2516604945 @default.
• W2920218480 cites W2561541975 @default.
• W2920218480 cites W2585534654 @default.
• W2920218480 cites W27434444 @default.
• W2920218480 cites W2763948036 @default.
• W2920218480 cites W2790379555 @default.
• W2920218480 cites W2912289066 @default.
• W2920218480 cites W2963930094 @default.
• W2920218480 cites W88657458 @default.
• W2920218480 doi "https://doi.org/10.1109/acssc.2018.8645464" @default.
• W2920218480 hasPublicationYear "2018" @default.
• W2920218480 type Work @default.
• W2920218480 sameAs 2920218480 @default.
• W2920218480 citedByCount "0" @default.
• W2920218480 crossrefType "proceedings-article" @default.
• W2920218480 hasAuthorship W2920218480A5001418995 @default.
• W2920218480 hasAuthorship W2920218480A5009808175 @default.
• W2920218480 hasAuthorship W2920218480A5021418299 @default.
• W2920218480 hasAuthorship W2920218480A5025896653 @default.
• W2920218480 hasBestOaLocation W29202184802 @default.
• W2920218480 hasConcept C105795698 @default.
• W2920218480 hasConcept C114614502 @default.
• W2920218480 hasConcept C119857082 @default.
• W2920218480 hasConcept C122280245 @default.
• W2920218480 hasConcept C12267149 @default.
• W2920218480 hasConcept C126255220 @default.
• W2920218480 hasConcept C134306372 @default.
• W2920218480 hasConcept C14036430 @default.
• W2920218480 hasConcept C152877465 @default.
• W2920218480 hasConcept C153258448 @default.
• W2920218480 hasConcept C154945302 @default.
• W2920218480 hasConcept C185429906 @default.
• W2920218480 hasConcept C206688291 @default.
• W2920218480 hasConcept C32834561 @default.
• W2920218480 hasConcept C33923547 @default.
• W2920218480 hasConcept C41008148 @default.
• W2920218480 hasConcept C50644808 @default.
• W2920218480 hasConcept C62799726 @default.
• W2920218480 hasConcept C74127309 @default.
• W2920218480 hasConcept C74193536 @default.
• W2920218480 hasConcept C78458016 @default.
• W2920218480 hasConcept C80884492 @default.
• W2920218480 hasConcept C86803240 @default.
• W2920218480 hasConceptScore W2920218480C105795698 @default.
• W2920218480 hasConceptScore W2920218480C114614502 @default.
• W2920218480 hasConceptScore W2920218480C119857082 @default.
• W2920218480 hasConceptScore W2920218480C122280245 @default.
• W2920218480 hasConceptScore W2920218480C12267149 @default.
• W2920218480 hasConceptScore W2920218480C126255220 @default.
• W2920218480 hasConceptScore W2920218480C134306372 @default.
• W2920218480 hasConceptScore W2920218480C14036430 @default.
• W2920218480 hasConceptScore W2920218480C152877465 @default.
• W2920218480 hasConceptScore W2920218480C153258448 @default.
• W2920218480 hasConceptScore W2920218480C154945302 @default.
• W2920218480 hasConceptScore W2920218480C185429906 @default.
• W2920218480 hasConceptScore W2920218480C206688291 @default.
• W2920218480 hasConceptScore W2920218480C32834561 @default.
• W2920218480 hasConceptScore W2920218480C33923547 @default.
• W2920218480 hasConceptScore W2920218480C41008148 @default.
• W2920218480 hasConceptScore W2920218480C50644808 @default.

• next