Matches in SemOpenAlex for { <https://semopenalex.org/work/W1830256639> ?p ?o ?g. }
- W1830256639 endingPage "1414" @default.
- W1830256639 startingPage "1408" @default.
- W1830256639 abstract "Side information is highly useful in the learning of a nonparametric kernel matrix. However, this often leads to an expensive semidefinite program (SDP). In recent years, a number of dedicated solvers have been proposed. Though much better than off-the-shelf SDP solvers, they still cannot scale to large data sets. In this paper, we propose a novel solver based on the alternating direction method of multipliers (ADMM). The key idea is to use a low-rank decomposition of the kernel matrix K = VTU, with the constraint that V = U. The resultant optimization problem, though non-convex, has favorable convergence properties and can be efficiently solved without requiring eigen-decomposition in each iteration. Experimental results on a number of real-world data sets demonstrate that the proposed method is as accurate as directly solving the SDP, but can be one to two orders of magnitude faster." @default.
- W1830256639 created "2016-06-24" @default.
- W1830256639 creator A5070273088 @default.
- W1830256639 creator A5081057351 @default.
- W1830256639 date "2013-08-03" @default.
- W1830256639 modified "2023-10-17" @default.
- W1830256639 title "Efficient kernel learning from side information using ADMM" @default.
- W1830256639 cites W1846534543 @default.
- W1830256639 cites W1984707692 @default.
- W1830256639 cites W2019713176 @default.
- W1830256639 cites W2031823405 @default.
- W1830256639 cites W2087941186 @default.
- W1830256639 cites W2097939965 @default.
- W1830256639 cites W2103788722 @default.
- W1830256639 cites W2104290444 @default.
- W1830256639 cites W2113592823 @default.
- W1830256639 cites W2130264611 @default.
- W1830256639 cites W2132914434 @default.
- W1830256639 cites W2134089414 @default.
- W1830256639 cites W2137557016 @default.
- W1830256639 cites W2145295623 @default.
- W1830256639 cites W2154462399 @default.
- W1830256639 cites W2164278908 @default.
- W1830256639 cites W2164535072 @default.
- W1830256639 cites W2183379929 @default.
- W1830256639 cites W2244987555 @default.
- W1830256639 cites W2285373897 @default.
- W1830256639 cites W2798909945 @default.
- W1830256639 cites W2912522929 @default.
- W1830256639 cites W3023786531 @default.
- W1830256639 cites W3147204795 @default.
- W1830256639 cites W3142913680 @default.
- W1830256639 hasPublicationYear "2013" @default.
- W1830256639 type Work @default.
- W1830256639 sameAs 1830256639 @default.
- W1830256639 citedByCount "2" @default.
- W1830256639 countsByYear W18302566392019 @default.
- W1830256639 crossrefType "proceedings-article" @default.
- W1830256639 hasAuthorship W1830256639A5070273088 @default.
- W1830256639 hasAuthorship W1830256639A5081057351 @default.
- W1830256639 hasConcept C106487976 @default.
- W1830256639 hasConcept C11413529 @default.
- W1830256639 hasConcept C114614502 @default.
- W1830256639 hasConcept C121332964 @default.
- W1830256639 hasConcept C126255220 @default.
- W1830256639 hasConcept C158693339 @default.
- W1830256639 hasConcept C159985019 @default.
- W1830256639 hasConcept C162324750 @default.
- W1830256639 hasConcept C164226766 @default.
- W1830256639 hasConcept C192562407 @default.
- W1830256639 hasConcept C2777303404 @default.
- W1830256639 hasConcept C2778770139 @default.
- W1830256639 hasConcept C33923547 @default.
- W1830256639 hasConcept C41008148 @default.
- W1830256639 hasConcept C42355184 @default.
- W1830256639 hasConcept C50522688 @default.
- W1830256639 hasConcept C62520636 @default.
- W1830256639 hasConcept C74193536 @default.
- W1830256639 hasConceptScore W1830256639C106487976 @default.
- W1830256639 hasConceptScore W1830256639C11413529 @default.
- W1830256639 hasConceptScore W1830256639C114614502 @default.
- W1830256639 hasConceptScore W1830256639C121332964 @default.
- W1830256639 hasConceptScore W1830256639C126255220 @default.
- W1830256639 hasConceptScore W1830256639C158693339 @default.
- W1830256639 hasConceptScore W1830256639C159985019 @default.
- W1830256639 hasConceptScore W1830256639C162324750 @default.
- W1830256639 hasConceptScore W1830256639C164226766 @default.
- W1830256639 hasConceptScore W1830256639C192562407 @default.
- W1830256639 hasConceptScore W1830256639C2777303404 @default.
- W1830256639 hasConceptScore W1830256639C2778770139 @default.
- W1830256639 hasConceptScore W1830256639C33923547 @default.
- W1830256639 hasConceptScore W1830256639C41008148 @default.
- W1830256639 hasConceptScore W1830256639C42355184 @default.
- W1830256639 hasConceptScore W1830256639C50522688 @default.
- W1830256639 hasConceptScore W1830256639C62520636 @default.
- W1830256639 hasConceptScore W1830256639C74193536 @default.
- W1830256639 hasOpenAccess W1830256639 @default.
- W1830256639 hasRelatedWork W107826715 @default.
- W1830256639 hasRelatedWork W1954327404 @default.
- W1830256639 hasRelatedWork W2013854956 @default.
- W1830256639 hasRelatedWork W2304424527 @default.
- W1830256639 hasRelatedWork W2520239196 @default.
- W1830256639 hasRelatedWork W2769646558 @default.
- W1830256639 hasRelatedWork W2770875486 @default.
- W1830256639 hasRelatedWork W2801613683 @default.
- W1830256639 hasRelatedWork W2807249433 @default.
- W1830256639 hasRelatedWork W2939022137 @default.
- W1830256639 hasRelatedWork W2978196696 @default.
- W1830256639 hasRelatedWork W2983997314 @default.
- W1830256639 hasRelatedWork W2990675203 @default.
- W1830256639 hasRelatedWork W2992468125 @default.
- W1830256639 hasRelatedWork W3003842237 @default.
- W1830256639 hasRelatedWork W3028588679 @default.
- W1830256639 hasRelatedWork W3042281785 @default.
- W1830256639 hasRelatedWork W3045369374 @default.
- W1830256639 hasRelatedWork W3100916622 @default.
- W1830256639 hasRelatedWork W3177200287 @default.
- W1830256639 isParatext "false" @default.