FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2898280316> ?p ?o ?g. }

• W2898280316 abstract "In this paper, we propose a Distributed Accumulated Newton Conjugate gradiEnt (DANCE) method in which sample size is gradually increasing to quickly obtain a solution whose empirical loss is under satisfactory statistical accuracy. Our proposed method is multistage in which the solution of a stage serves as a warm start for the next stage which contains more samples (including the samples in the previous stage). The proposed multistage algorithm reduces the number of passes over data to achieve the statistical accuracy of the full training set. Moreover, our algorithm in nature is easy to be distributed and shares the strong scaling property indicating that acceleration is always expected by using more computing nodes. Various iteration complexity results regarding descent direction computation, communication efficiency and stopping criteria are analyzed under convex setting. Our numerical results illustrate that the proposed method outperforms other comparable methods for solving learning problems including neural networks." @default.
• W2898280316 created "2018-11-02" @default.
• W2898280316 creator A5008417632 @default.
• W2898280316 creator A5023893507 @default.
• W2898280316 creator A5064222013 @default.
• W2898280316 creator A5066366329 @default.
• W2898280316 creator A5069885740 @default.
• W2898280316 creator A5070679093 @default.
• W2898280316 creator A5078862959 @default.
• W2898280316 date "2018-10-26" @default.
• W2898280316 modified "2023-10-16" @default.
• W2898280316 title "Efficient Distributed Hessian Free Algorithm for Large-scale Empirical Risk Minimization via Accumulating Sample Strategy" @default.
• W2898280316 cites W114517082 @default.
• W2898280316 cites W1491622225 @default.
• W2898280316 cites W1505356468 @default.
• W2898280316 cites W1522301498 @default.
• W2898280316 cites W1592294486 @default.
• W2898280316 cites W1697545848 @default.
• W2898280316 cites W1982032418 @default.
• W2898280316 cites W2001032894 @default.
• W2898280316 cites W2100556411 @default.
• W2898280316 cites W2105875671 @default.
• W2898280316 cites W2107438106 @default.
• W2898280316 cites W2113651538 @default.
• W2898280316 cites W2153635508 @default.
• W2898280316 cites W2298776138 @default.
• W2898280316 cites W2500214046 @default.
• W2898280316 cites W2760953462 @default.
• W2898280316 cites W2899771611 @default.
• W2898280316 cites W2900789157 @default.
• W2898280316 cites W2913310393 @default.
• W2898280316 cites W2947740176 @default.
• W2898280316 cites W2952215077 @default.
• W2898280316 cites W2952594493 @default.
• W2898280316 cites W2962696654 @default.
• W2898280316 cites W2962969021 @default.
• W2898280316 cites W2962986403 @default.
• W2898280316 cites W2963087817 @default.
• W2898280316 cites W2963653623 @default.
• W2898280316 cites W2963818924 @default.
• W2898280316 cites W2963941964 @default.
• W2898280316 cites W2964093568 @default.
• W2898280316 cites W3131485729 @default.
• W2898280316 hasPublicationYear "2018" @default.
• W2898280316 type Work @default.
• W2898280316 sameAs 2898280316 @default.
• W2898280316 citedByCount "8" @default.
• W2898280316 countsByYear W28982803162019 @default.
• W2898280316 countsByYear W28982803162020 @default.
• W2898280316 countsByYear W28982803162021 @default.
• W2898280316 crossrefType "posted-content" @default.
• W2898280316 hasAuthorship W2898280316A5008417632 @default.
• W2898280316 hasAuthorship W2898280316A5023893507 @default.
• W2898280316 hasAuthorship W2898280316A5064222013 @default.
• W2898280316 hasAuthorship W2898280316A5066366329 @default.
• W2898280316 hasAuthorship W2898280316A5069885740 @default.
• W2898280316 hasAuthorship W2898280316A5070679093 @default.
• W2898280316 hasAuthorship W2898280316A5078862959 @default.
• W2898280316 hasConcept C107321475 @default.
• W2898280316 hasConcept C112680207 @default.
• W2898280316 hasConcept C11413529 @default.
• W2898280316 hasConcept C117896860 @default.
• W2898280316 hasConcept C121332964 @default.
• W2898280316 hasConcept C126255220 @default.
• W2898280316 hasConcept C145446738 @default.
• W2898280316 hasConcept C153258448 @default.
• W2898280316 hasConcept C154945302 @default.
• W2898280316 hasConcept C177264268 @default.
• W2898280316 hasConcept C185592680 @default.
• W2898280316 hasConcept C198531522 @default.
• W2898280316 hasConcept C199360897 @default.
• W2898280316 hasConcept C203616005 @default.
• W2898280316 hasConcept C2524010 @default.
• W2898280316 hasConcept C28826006 @default.
• W2898280316 hasConcept C33923547 @default.
• W2898280316 hasConcept C41008148 @default.
• W2898280316 hasConcept C43617362 @default.
• W2898280316 hasConcept C45374587 @default.
• W2898280316 hasConcept C50644808 @default.
• W2898280316 hasConcept C74650414 @default.
• W2898280316 hasConcept C81184566 @default.
• W2898280316 hasConceptScore W2898280316C107321475 @default.
• W2898280316 hasConceptScore W2898280316C112680207 @default.
• W2898280316 hasConceptScore W2898280316C11413529 @default.
• W2898280316 hasConceptScore W2898280316C117896860 @default.
• W2898280316 hasConceptScore W2898280316C121332964 @default.
• W2898280316 hasConceptScore W2898280316C126255220 @default.
• W2898280316 hasConceptScore W2898280316C145446738 @default.
• W2898280316 hasConceptScore W2898280316C153258448 @default.
• W2898280316 hasConceptScore W2898280316C154945302 @default.
• W2898280316 hasConceptScore W2898280316C177264268 @default.
• W2898280316 hasConceptScore W2898280316C185592680 @default.
• W2898280316 hasConceptScore W2898280316C198531522 @default.
• W2898280316 hasConceptScore W2898280316C199360897 @default.
• W2898280316 hasConceptScore W2898280316C203616005 @default.
• W2898280316 hasConceptScore W2898280316C2524010 @default.
• W2898280316 hasConceptScore W2898280316C28826006 @default.
• W2898280316 hasConceptScore W2898280316C33923547 @default.
• W2898280316 hasConceptScore W2898280316C41008148 @default.
• W2898280316 hasConceptScore W2898280316C43617362 @default.

• next