FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3175002498> ?p ?o ?g. }

• W3175002498 endingPage "7817" @default.
• W3175002498 startingPage "7806" @default.
• W3175002498 abstract "Recently, stochastic hard thresholding (HT) optimization methods [e.g., stochastic variance reduced gradient hard thresholding (SVRGHT)] are becoming more attractive for solving large-scale sparsity/rank-constrained problems. However, they have much higher HT oracle complexities, especially for high-dimensional data or large-scale matrices. To address this issue and inspired by the well-known Gradient Support Pursuit (GraSP) method, this article proposes a new Relaxed Gradient Support Pursuit (RGraSP) framework. Unlike GraSP, RGraSP only requires to yield an approximation solution at each iteration. Based on the property of RGraSP, we also present an efficient stochastic variance reduction-gradient support pursuit algorithm and its fast version (called stochastic variance reduced gradient support pursuit (SVRGSP+). We prove that the gradient oracle complexity of both our algorithms is two times less than that of SVRGHT. In particular, their HT complexity is about <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$kappa _{widehat {s}}$ </tex-math></inline-formula> times less than that of SVRGHT, where <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$kappa _{widehat {s}}$ </tex-math></inline-formula> is the restricted condition number. Moreover, we prove that our algorithms enjoy fast linear convergence to an approximately global optimum, and also present an asynchronous parallel variant to deal with very high-dimensional and sparse data. Experimental results on both synthetic and real-world datasets show that our algorithms yield superior results than the state-of-the-art gradient HT methods." @default.
• W3175002498 created "2021-07-05" @default.
• W3175002498 creator A5010883708 @default.
• W3175002498 creator A5054464310 @default.
• W3175002498 creator A5067858777 @default.
• W3175002498 creator A5076351250 @default.
• W3175002498 creator A5077622519 @default.
• W3175002498 creator A5091227928 @default.
• W3175002498 date "2022-12-01" @default.
• W3175002498 modified "2023-10-16" @default.
• W3175002498 title "Efficient Gradient Support Pursuit With Less Hard Thresholding for Cardinality-Constrained Learning" @default.
• W3175002498 cites W1977520307 @default.
• W3175002498 cites W1994520254 @default.
• W3175002498 cites W2017761965 @default.
• W3175002498 cites W2074682976 @default.
• W3175002498 cites W2084745075 @default.
• W3175002498 cites W2103628399 @default.
• W3175002498 cites W2107861471 @default.
• W3175002498 cites W2118550318 @default.
• W3175002498 cites W2127271355 @default.
• W3175002498 cites W2135046866 @default.
• W3175002498 cites W2151693816 @default.
• W3175002498 cites W2162708633 @default.
• W3175002498 cites W2345068797 @default.
• W3175002498 cites W2727020975 @default.
• W3175002498 cites W2744964614 @default.
• W3175002498 cites W2808381739 @default.
• W3175002498 cites W2962791795 @default.
• W3175002498 cites W2962952793 @default.
• W3175002498 cites W2963297739 @default.
• W3175002498 cites W2963322354 @default.
• W3175002498 cites W2963941964 @default.
• W3175002498 cites W2964185543 @default.
• W3175002498 cites W2965897141 @default.
• W3175002498 cites W2983222335 @default.
• W3175002498 cites W2998383793 @default.
• W3175002498 cites W3048822613 @default.
• W3175002498 cites W3102942031 @default.
• W3175002498 doi "https://doi.org/10.1109/tnnls.2021.3087805" @default.
• W3175002498 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34161247" @default.
• W3175002498 hasPublicationYear "2022" @default.
• W3175002498 type Work @default.
• W3175002498 sameAs 3175002498 @default.
• W3175002498 citedByCount "0" @default.
• W3175002498 crossrefType "journal-article" @default.
• W3175002498 hasAuthorship W3175002498A5010883708 @default.
• W3175002498 hasAuthorship W3175002498A5054464310 @default.
• W3175002498 hasAuthorship W3175002498A5067858777 @default.
• W3175002498 hasAuthorship W3175002498A5076351250 @default.
• W3175002498 hasAuthorship W3175002498A5077622519 @default.
• W3175002498 hasAuthorship W3175002498A5091227928 @default.
• W3175002498 hasConcept C105795698 @default.
• W3175002498 hasConcept C11413529 @default.
• W3175002498 hasConcept C115903868 @default.
• W3175002498 hasConcept C115961682 @default.
• W3175002498 hasConcept C124101348 @default.
• W3175002498 hasConcept C136764020 @default.
• W3175002498 hasConcept C154945302 @default.
• W3175002498 hasConcept C191178318 @default.
• W3175002498 hasConcept C19499675 @default.
• W3175002498 hasConcept C206688291 @default.
• W3175002498 hasConcept C33923547 @default.
• W3175002498 hasConcept C37616216 @default.
• W3175002498 hasConcept C41008148 @default.
• W3175002498 hasConcept C45357846 @default.
• W3175002498 hasConcept C50644808 @default.
• W3175002498 hasConcept C55166926 @default.
• W3175002498 hasConcept C62644790 @default.
• W3175002498 hasConcept C81184566 @default.
• W3175002498 hasConcept C87117476 @default.
• W3175002498 hasConcept C94375191 @default.
• W3175002498 hasConceptScore W3175002498C105795698 @default.
• W3175002498 hasConceptScore W3175002498C11413529 @default.
• W3175002498 hasConceptScore W3175002498C115903868 @default.
• W3175002498 hasConceptScore W3175002498C115961682 @default.
• W3175002498 hasConceptScore W3175002498C124101348 @default.
• W3175002498 hasConceptScore W3175002498C136764020 @default.
• W3175002498 hasConceptScore W3175002498C154945302 @default.
• W3175002498 hasConceptScore W3175002498C191178318 @default.
• W3175002498 hasConceptScore W3175002498C19499675 @default.
• W3175002498 hasConceptScore W3175002498C206688291 @default.
• W3175002498 hasConceptScore W3175002498C33923547 @default.
• W3175002498 hasConceptScore W3175002498C37616216 @default.
• W3175002498 hasConceptScore W3175002498C41008148 @default.
• W3175002498 hasConceptScore W3175002498C45357846 @default.
• W3175002498 hasConceptScore W3175002498C50644808 @default.
• W3175002498 hasConceptScore W3175002498C55166926 @default.
• W3175002498 hasConceptScore W3175002498C62644790 @default.
• W3175002498 hasConceptScore W3175002498C81184566 @default.
• W3175002498 hasConceptScore W3175002498C87117476 @default.
• W3175002498 hasConceptScore W3175002498C94375191 @default.
• W3175002498 hasFunder F4320321001 @default.
• W3175002498 hasIssue "12" @default.
• W3175002498 hasLocation W31750024981 @default.
• W3175002498 hasLocation W31750024982 @default.
• W3175002498 hasOpenAccess W3175002498 @default.
• W3175002498 hasPrimaryLocation W31750024981 @default.
• W3175002498 hasRelatedWork W2127724926 @default.

• next