Matches in SemOpenAlex for { <https://semopenalex.org/work/W3047486051> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W3047486051 abstract "Distributed learning facilitates the scaling-up of data processing by distributing the computational burden over several nodes. Despite the vast interest in distributed learning, generalization performance of such approaches is not well understood. We address this gap by focusing on a linear regression setting. We consider the setting where the unknowns are distributed over a network of nodes. We present an analytical characterization of the dependence of the generalization error on the partitioning of the unknowns over nodes. In particular, for the overparameterized case, our results show that while the error on training data remains in the same range as that of the centralized solution, the generalization error of the distributed solution increases dramatically compared to that of the centralized solution when the number of unknowns estimated at any node is close to the number of observations. We further provide numerical examples to verify our analytical expressions." @default.
- W3047486051 created "2020-08-10" @default.
- W3047486051 creator A5009683515 @default.
- W3047486051 creator A5050844254 @default.
- W3047486051 creator A5084552239 @default.
- W3047486051 date "2020-05-01" @default.
- W3047486051 modified "2023-09-23" @default.
- W3047486051 title "Generalization Error for Linear Regression under Distributed Learning" @default.
- W3047486051 cites W2003202757 @default.
- W3047486051 cites W2107568926 @default.
- W3047486051 cites W2154834860 @default.
- W3047486051 cites W2809130164 @default.
- W3047486051 cites W2962814013 @default.
- W3047486051 cites W2963518130 @default.
- W3047486051 cites W3047486051 @default.
- W3047486051 doi "https://doi.org/10.1109/spawc48557.2020.9154284" @default.
- W3047486051 hasPublicationYear "2020" @default.
- W3047486051 type Work @default.
- W3047486051 sameAs 3047486051 @default.
- W3047486051 citedByCount "6" @default.
- W3047486051 countsByYear W30474860512020 @default.
- W3047486051 countsByYear W30474860512021 @default.
- W3047486051 countsByYear W30474860512023 @default.
- W3047486051 crossrefType "proceedings-article" @default.
- W3047486051 hasAuthorship W3047486051A5009683515 @default.
- W3047486051 hasAuthorship W3047486051A5050844254 @default.
- W3047486051 hasAuthorship W3047486051A5084552239 @default.
- W3047486051 hasBestOaLocation W30474860512 @default.
- W3047486051 hasConcept C105795698 @default.
- W3047486051 hasConcept C117765406 @default.
- W3047486051 hasConcept C119857082 @default.
- W3047486051 hasConcept C134306372 @default.
- W3047486051 hasConcept C152877465 @default.
- W3047486051 hasConcept C154945302 @default.
- W3047486051 hasConcept C177148314 @default.
- W3047486051 hasConcept C32224588 @default.
- W3047486051 hasConcept C33923547 @default.
- W3047486051 hasConcept C41008148 @default.
- W3047486051 hasConcept C48921125 @default.
- W3047486051 hasConcept C50644808 @default.
- W3047486051 hasConcept C64946054 @default.
- W3047486051 hasConcept C83546350 @default.
- W3047486051 hasConceptScore W3047486051C105795698 @default.
- W3047486051 hasConceptScore W3047486051C117765406 @default.
- W3047486051 hasConceptScore W3047486051C119857082 @default.
- W3047486051 hasConceptScore W3047486051C134306372 @default.
- W3047486051 hasConceptScore W3047486051C152877465 @default.
- W3047486051 hasConceptScore W3047486051C154945302 @default.
- W3047486051 hasConceptScore W3047486051C177148314 @default.
- W3047486051 hasConceptScore W3047486051C32224588 @default.
- W3047486051 hasConceptScore W3047486051C33923547 @default.
- W3047486051 hasConceptScore W3047486051C41008148 @default.
- W3047486051 hasConceptScore W3047486051C48921125 @default.
- W3047486051 hasConceptScore W3047486051C50644808 @default.
- W3047486051 hasConceptScore W3047486051C64946054 @default.
- W3047486051 hasConceptScore W3047486051C83546350 @default.
- W3047486051 hasLocation W30474860511 @default.
- W3047486051 hasLocation W30474860512 @default.
- W3047486051 hasLocation W30474860513 @default.
- W3047486051 hasOpenAccess W3047486051 @default.
- W3047486051 hasPrimaryLocation W30474860511 @default.
- W3047486051 hasRelatedWork W1546472494 @default.
- W3047486051 hasRelatedWork W2074089485 @default.
- W3047486051 hasRelatedWork W2117131941 @default.
- W3047486051 hasRelatedWork W2169537700 @default.
- W3047486051 hasRelatedWork W2364467608 @default.
- W3047486051 hasRelatedWork W2589006171 @default.
- W3047486051 hasRelatedWork W267133670 @default.
- W3047486051 hasRelatedWork W2886532972 @default.
- W3047486051 hasRelatedWork W3118299338 @default.
- W3047486051 hasRelatedWork W4308419583 @default.
- W3047486051 isParatext "false" @default.
- W3047486051 isRetracted "false" @default.
- W3047486051 magId "3047486051" @default.
- W3047486051 workType "article" @default.