Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313452328> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4313452328 endingPage "025003" @default.
- W4313452328 startingPage "025003" @default.
- W4313452328 abstract "Abstract This paper considers spectral pairwise ranking algorithms in a reproducing kernel Hilbert space. The concerned algorithms include a large family of regularized pairwise learning algorithms. Motivated by regularization methods, spectral algorithms are proposed to solve ill-posed linear inverse problems, then developed in learning theory and inverse problems. Recently, pairwise learning tasks such as bipartite ranking, similarity metric learning, Minimum Error Entropy principle, and AUC maximization have received increasing attention due to their wide applications. However, the spectral algorithm acts on the spectrum of the empirical integral operator or kernel matrix, involving the singular value decomposition or the inverse of the matrix, which is time-consuming when the sample size is immense. Our contribution is twofold. First, under some general source conditions and capacity assumptions, we establish the first-ever mini-max optimal convergence rates for spectral pairwise ranking algorithms. Second, we consider the distributed version of the algorithms based on a divide-and-conquer approach and show that, as long as the partition of the data set is not too large, the distributed learning algorithm enjoys both computational efficiency and statistical optimality." @default.
- W4313452328 created "2023-01-06" @default.
- W4313452328 creator A5031879053 @default.
- W4313452328 creator A5042860923 @default.
- W4313452328 creator A5059680084 @default.
- W4313452328 date "2022-12-30" @default.
- W4313452328 modified "2023-10-16" @default.
- W4313452328 title "Distributed spectral pairwise ranking algorithms" @default.
- W4313452328 cites W1564947197 @default.
- W4313452328 cites W1970781863 @default.
- W4313452328 cites W1978810924 @default.
- W4313452328 cites W1986280275 @default.
- W4313452328 cites W1987757535 @default.
- W4313452328 cites W2012501405 @default.
- W4313452328 cites W2014963263 @default.
- W4313452328 cites W2030811942 @default.
- W4313452328 cites W2034320649 @default.
- W4313452328 cites W2035642106 @default.
- W4313452328 cites W2047221353 @default.
- W4313452328 cites W2109668081 @default.
- W4313452328 cites W2123845705 @default.
- W4313452328 cites W2139039274 @default.
- W4313452328 cites W2143331230 @default.
- W4313452328 cites W2165591566 @default.
- W4313452328 cites W2221340659 @default.
- W4313452328 cites W2274052023 @default.
- W4313452328 cites W2607329908 @default.
- W4313452328 cites W2613940844 @default.
- W4313452328 cites W2700204661 @default.
- W4313452328 cites W2792024940 @default.
- W4313452328 cites W2900243757 @default.
- W4313452328 cites W2911067482 @default.
- W4313452328 cites W2963053844 @default.
- W4313452328 cites W2964017994 @default.
- W4313452328 cites W2969928494 @default.
- W4313452328 cites W4237853473 @default.
- W4313452328 doi "https://doi.org/10.1088/1361-6420/acad23" @default.
- W4313452328 hasPublicationYear "2022" @default.
- W4313452328 type Work @default.
- W4313452328 citedByCount "0" @default.
- W4313452328 crossrefType "journal-article" @default.
- W4313452328 hasAuthorship W4313452328A5031879053 @default.
- W4313452328 hasAuthorship W4313452328A5042860923 @default.
- W4313452328 hasAuthorship W4313452328A5059680084 @default.
- W4313452328 hasConcept C105795698 @default.
- W4313452328 hasConcept C11413529 @default.
- W4313452328 hasConcept C126255220 @default.
- W4313452328 hasConcept C134306372 @default.
- W4313452328 hasConcept C184898388 @default.
- W4313452328 hasConcept C22789450 @default.
- W4313452328 hasConcept C33923547 @default.
- W4313452328 hasConcept C62799726 @default.
- W4313452328 hasConcept C80884492 @default.
- W4313452328 hasConceptScore W4313452328C105795698 @default.
- W4313452328 hasConceptScore W4313452328C11413529 @default.
- W4313452328 hasConceptScore W4313452328C126255220 @default.
- W4313452328 hasConceptScore W4313452328C134306372 @default.
- W4313452328 hasConceptScore W4313452328C184898388 @default.
- W4313452328 hasConceptScore W4313452328C22789450 @default.
- W4313452328 hasConceptScore W4313452328C33923547 @default.
- W4313452328 hasConceptScore W4313452328C62799726 @default.
- W4313452328 hasConceptScore W4313452328C80884492 @default.
- W4313452328 hasFunder F4320321001 @default.
- W4313452328 hasFunder F4320335787 @default.
- W4313452328 hasIssue "2" @default.
- W4313452328 hasLocation W43134523281 @default.
- W4313452328 hasOpenAccess W4313452328 @default.
- W4313452328 hasPrimaryLocation W43134523281 @default.
- W4313452328 hasRelatedWork W1969435400 @default.
- W4313452328 hasRelatedWork W2045473855 @default.
- W4313452328 hasRelatedWork W2055872486 @default.
- W4313452328 hasRelatedWork W2091490647 @default.
- W4313452328 hasRelatedWork W2158677029 @default.
- W4313452328 hasRelatedWork W2161345883 @default.
- W4313452328 hasRelatedWork W2892153240 @default.
- W4313452328 hasRelatedWork W2977833117 @default.
- W4313452328 hasRelatedWork W2982521376 @default.
- W4313452328 hasRelatedWork W3084216571 @default.
- W4313452328 hasVolume "39" @default.
- W4313452328 isParatext "false" @default.
- W4313452328 isRetracted "false" @default.
- W4313452328 workType "article" @default.