FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3210150632> ?p ?o ?g. }

• W3210150632 abstract "This paper aims to propose and theoretically analyze a new distributed schemefor sparse linear regression and feature selection. The primary goal is tolearn the few causal features of a high-dimensional dataset based on noisyobservations from an unknown sparse linear model. However, the presumedtraining set which includes $n$ data samples in $mathbb{R}^p$ is alreadydistributed over a large network with $N$ clients connected through extremelylow-bandwidth links. Also, we consider the asymptotic configuration of $1llNll nll p$. In order to infer the causal dimensions from the whole dataset,we propose a simple, yet effective method for information sharing in thenetwork. In this regard, we theoretically show that the true causal featurescan be reliably recovered with negligible bandwidth usage of $Oleft(Nlogpright)$ across the network. This yields a significantly lower communicationcost in comparison with the trivial case of transmitting all the samples to asingle node (centralized scenario), which requires $Oleft(npright)$transmissions. Even more sophisticated schemes such as ADMM still have acommunication complexity of $Oleft(Npright)$. Surprisingly, our samplecomplexity bound is proved to be the same (up to a constant factor) as theoptimal centralized approach for a fixed performance measure in each node,while that of a na{i}ve decentralized technique grows linearly with $N$.Theoretical guarantees in this paper are based on the recent analytic frameworkof debiased LASSO in Javanmard et al. (2019), and are supported by severalcomputer experiments performed on both synthetic and real-world datasets." @default.
• W3210150632 created "2021-11-08" @default.
• W3210150632 creator A5018408976 @default.
• W3210150632 creator A5032369453 @default.
• W3210150632 creator A5049074026 @default.
• W3210150632 date "2021-11-02" @default.
• W3210150632 modified "2023-09-27" @default.
• W3210150632 title "Distributed Sparse Feature Selection in Communication-Restricted Networks." @default.
• W3210150632 cites W1429921896 @default.
• W3210150632 cites W1557269292 @default.
• W3210150632 cites W1577912871 @default.
• W3210150632 cites W1969251723 @default.
• W3210150632 cites W1980454827 @default.
• W3210150632 cites W1982545958 @default.
• W3210150632 cites W2021624181 @default.
• W3210150632 cites W2040369763 @default.
• W3210150632 cites W2045079045 @default.
• W3210150632 cites W2069119359 @default.
• W3210150632 cites W2071607622 @default.
• W3210150632 cites W2105693192 @default.
• W3210150632 cites W2128685318 @default.
• W3210150632 cites W2135046866 @default.
• W3210150632 cites W2164278908 @default.
• W3210150632 cites W2244987555 @default.
• W3210150632 cites W2294690908 @default.
• W3210150632 cites W2525549348 @default.
• W3210150632 cites W2541884796 @default.
• W3210150632 cites W2595198670 @default.
• W3210150632 cites W2796083132 @default.
• W3210150632 cites W2912494791 @default.
• W3210150632 cites W2962741697 @default.
• W3210150632 cites W2963013132 @default.
• W3210150632 cites W2963322354 @default.
• W3210150632 cites W2963502225 @default.
• W3210150632 cites W2964166170 @default.
• W3210150632 cites W2964345095 @default.
• W3210150632 cites W2971170030 @default.
• W3210150632 cites W2996320429 @default.
• W3210150632 cites W3002588575 @default.
• W3210150632 cites W3086394069 @default.
• W3210150632 cites W3099550161 @default.
• W3210150632 cites W3102479286 @default.
• W3210150632 cites W3103375666 @default.
• W3210150632 cites W3121306115 @default.
• W3210150632 cites W3121333339 @default.
• W3210150632 cites W3122883274 @default.
• W3210150632 cites W3159009033 @default.
• W3210150632 hasPublicationYear "2021" @default.
• W3210150632 type Work @default.
• W3210150632 sameAs 3210150632 @default.
• W3210150632 citedByCount "0" @default.
• W3210150632 crossrefType "posted-content" @default.
• W3210150632 hasAuthorship W3210150632A5018408976 @default.
• W3210150632 hasAuthorship W3210150632A5032369453 @default.
• W3210150632 hasAuthorship W3210150632A5049074026 @default.
• W3210150632 hasConcept C11413529 @default.
• W3210150632 hasConcept C114614502 @default.
• W3210150632 hasConcept C119857082 @default.
• W3210150632 hasConcept C127413603 @default.
• W3210150632 hasConcept C136764020 @default.
• W3210150632 hasConcept C138885662 @default.
• W3210150632 hasConcept C148483581 @default.
• W3210150632 hasConcept C154945302 @default.
• W3210150632 hasConcept C177264268 @default.
• W3210150632 hasConcept C179145077 @default.
• W3210150632 hasConcept C199360897 @default.
• W3210150632 hasConcept C2776257435 @default.
• W3210150632 hasConcept C2776401178 @default.
• W3210150632 hasConcept C2777027219 @default.
• W3210150632 hasConcept C31258907 @default.
• W3210150632 hasConcept C33923547 @default.
• W3210150632 hasConcept C37616216 @default.
• W3210150632 hasConcept C41008148 @default.
• W3210150632 hasConcept C41895202 @default.
• W3210150632 hasConcept C48921125 @default.
• W3210150632 hasConcept C62611344 @default.
• W3210150632 hasConcept C63553672 @default.
• W3210150632 hasConcept C66938386 @default.
• W3210150632 hasConceptScore W3210150632C11413529 @default.
• W3210150632 hasConceptScore W3210150632C114614502 @default.
• W3210150632 hasConceptScore W3210150632C119857082 @default.
• W3210150632 hasConceptScore W3210150632C127413603 @default.
• W3210150632 hasConceptScore W3210150632C136764020 @default.
• W3210150632 hasConceptScore W3210150632C138885662 @default.
• W3210150632 hasConceptScore W3210150632C148483581 @default.
• W3210150632 hasConceptScore W3210150632C154945302 @default.
• W3210150632 hasConceptScore W3210150632C177264268 @default.
• W3210150632 hasConceptScore W3210150632C179145077 @default.
• W3210150632 hasConceptScore W3210150632C199360897 @default.
• W3210150632 hasConceptScore W3210150632C2776257435 @default.
• W3210150632 hasConceptScore W3210150632C2776401178 @default.
• W3210150632 hasConceptScore W3210150632C2777027219 @default.
• W3210150632 hasConceptScore W3210150632C31258907 @default.
• W3210150632 hasConceptScore W3210150632C33923547 @default.
• W3210150632 hasConceptScore W3210150632C37616216 @default.
• W3210150632 hasConceptScore W3210150632C41008148 @default.
• W3210150632 hasConceptScore W3210150632C41895202 @default.
• W3210150632 hasConceptScore W3210150632C48921125 @default.
• W3210150632 hasConceptScore W3210150632C62611344 @default.
• W3210150632 hasConceptScore W3210150632C63553672 @default.

• next