Matches in SemOpenAlex for { <https://semopenalex.org/work/W2196761959> ?p ?o ?g. }
- W2196761959 abstract "Learning sparse combinations is a frequent theme in machine learning. In this paper, we study its associated optimization problem in the distributed setting where the elements to be combined are not centrally located but spread over a network. We address the key challenges of balancing communication costs and optimization errors. To this end, we propose a distributed Frank-Wolfe (dFW) algorithm. We obtain theoretical guarantees on the optimization error $epsilon$ and communication cost that do not depend on the total number of combining elements. We further show that the communication cost of dFW is optimal by deriving a lower-bound on the communication cost required to construct an $epsilon$-approximate solution. We validate our theoretical analysis with empirical studies on synthetic and real-world data, which demonstrate that dFW outperforms both baselines and competing methods. We also study the performance of dFW when the conditions of our analysis are relaxed, and show that dFW is fairly robust." @default.
- W2196761959 created "2016-06-24" @default.
- W2196761959 creator A5012371482 @default.
- W2196761959 creator A5014504793 @default.
- W2196761959 creator A5021516103 @default.
- W2196761959 creator A5035905957 @default.
- W2196761959 creator A5068544954 @default.
- W2196761959 date "2014-04-09" @default.
- W2196761959 modified "2023-10-18" @default.
- W2196761959 title "A Distributed Frank-Wolfe Algorithm for Communication-Efficient Sparse Learning" @default.
- W2196761959 cites W139031692 @default.
- W2196761959 cites W144982758 @default.
- W2196761959 cites W1464850230 @default.
- W2196761959 cites W1495909821 @default.
- W2196761959 cites W150939725 @default.
- W2196761959 cites W1599482965 @default.
- W2196761959 cites W1973264045 @default.
- W2196761959 cites W1981773323 @default.
- W2196761959 cites W1987492370 @default.
- W2196761959 cites W199097577 @default.
- W2196761959 cites W1994520254 @default.
- W2196761959 cites W2003208028 @default.
- W2196761959 cites W2013243898 @default.
- W2196761959 cites W2031823405 @default.
- W2196761959 cites W2035484943 @default.
- W2196761959 cites W2046387702 @default.
- W2196761959 cites W2106521131 @default.
- W2196761959 cites W2109706083 @default.
- W2196761959 cites W2113606819 @default.
- W2196761959 cites W2114204610 @default.
- W2196761959 cites W2114296561 @default.
- W2196761959 cites W2116148865 @default.
- W2196761959 cites W2119821739 @default.
- W2196761959 cites W2123154536 @default.
- W2196761959 cites W2125607229 @default.
- W2196761959 cites W2130062883 @default.
- W2196761959 cites W2132291180 @default.
- W2196761959 cites W2135046866 @default.
- W2196761959 cites W2136360692 @default.
- W2196761959 cites W2136885855 @default.
- W2196761959 cites W2138019504 @default.
- W2196761959 cites W2152734820 @default.
- W2196761959 cites W2152799677 @default.
- W2196761959 cites W2155319834 @default.
- W2196761959 cites W2164278908 @default.
- W2196761959 cites W2170735271 @default.
- W2196761959 cites W2247185167 @default.
- W2196761959 cites W2952152543 @default.
- W2196761959 cites W2963405668 @default.
- W2196761959 cites W2964023411 @default.
- W2196761959 cites W2964181194 @default.
- W2196761959 cites W2964262905 @default.
- W2196761959 cites W905619 @default.
- W2196761959 doi "https://doi.org/10.48550/arxiv.1404.2644" @default.
- W2196761959 hasPublicationYear "2014" @default.
- W2196761959 type Work @default.
- W2196761959 sameAs 2196761959 @default.
- W2196761959 citedByCount "1" @default.
- W2196761959 countsByYear W21967619592014 @default.
- W2196761959 crossrefType "posted-content" @default.
- W2196761959 hasAuthorship W2196761959A5012371482 @default.
- W2196761959 hasAuthorship W2196761959A5014504793 @default.
- W2196761959 hasAuthorship W2196761959A5021516103 @default.
- W2196761959 hasAuthorship W2196761959A5035905957 @default.
- W2196761959 hasAuthorship W2196761959A5068544954 @default.
- W2196761959 hasBestOaLocation W21967619591 @default.
- W2196761959 hasConcept C11413529 @default.
- W2196761959 hasConcept C119857082 @default.
- W2196761959 hasConcept C126255220 @default.
- W2196761959 hasConcept C137836250 @default.
- W2196761959 hasConcept C154945302 @default.
- W2196761959 hasConcept C26517878 @default.
- W2196761959 hasConcept C2780801425 @default.
- W2196761959 hasConcept C2987595161 @default.
- W2196761959 hasConcept C31258907 @default.
- W2196761959 hasConcept C33923547 @default.
- W2196761959 hasConcept C38652104 @default.
- W2196761959 hasConcept C41008148 @default.
- W2196761959 hasConceptScore W2196761959C11413529 @default.
- W2196761959 hasConceptScore W2196761959C119857082 @default.
- W2196761959 hasConceptScore W2196761959C126255220 @default.
- W2196761959 hasConceptScore W2196761959C137836250 @default.
- W2196761959 hasConceptScore W2196761959C154945302 @default.
- W2196761959 hasConceptScore W2196761959C26517878 @default.
- W2196761959 hasConceptScore W2196761959C2780801425 @default.
- W2196761959 hasConceptScore W2196761959C2987595161 @default.
- W2196761959 hasConceptScore W2196761959C31258907 @default.
- W2196761959 hasConceptScore W2196761959C33923547 @default.
- W2196761959 hasConceptScore W2196761959C38652104 @default.
- W2196761959 hasConceptScore W2196761959C41008148 @default.
- W2196761959 hasLocation W21967619591 @default.
- W2196761959 hasLocation W21967619592 @default.
- W2196761959 hasLocation W21967619593 @default.
- W2196761959 hasLocation W21967619594 @default.
- W2196761959 hasOpenAccess W2196761959 @default.
- W2196761959 hasPrimaryLocation W21967619591 @default.
- W2196761959 hasRelatedWork W2031052090 @default.
- W2196761959 hasRelatedWork W2031202609 @default.
- W2196761959 hasRelatedWork W2122227724 @default.
- W2196761959 hasRelatedWork W2373545044 @default.