Matches in SemOpenAlex for { <https://semopenalex.org/work/W2274052023> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W2274052023 endingPage "777" @default.
- W2274052023 startingPage "743" @default.
- W2274052023 abstract "Pairwise learning usually refers to a learning task that involves a loss function depending on pairs of examples, among which the most notable ones are bipartite ranking, metric learning, and AUC maximization. In this letter we study an online algorithm for pairwise learning with a least-square loss function in an unconstrained setting of a reproducing kernel Hilbert space (RKHS) that we refer to as the Online Pairwise lEaRning Algorithm (OPERA). In contrast to existing works (Kar, Sriperumbudur, Jain, & Karnick, 2013 ; Wang, Khardon, Pechyony, & Jones, 2012 ), which require that the iterates are restricted to a bounded domain or the loss function is strongly convex, OPERA is associated with a non-strongly convex objective function and learns the target function in an unconstrained RKHS. Specifically, we establish a general theorem that guarantees the almost sure convergence for the last iterate of OPERA without any assumptions on the underlying distribution. Explicit convergence rates are derived under the condition of polynomially decaying step sizes. We also establish an interesting property for a family of widely used kernels in the setting of pairwise learning and illustrate the convergence results using such kernels. Our methodology mainly depends on the characterization of RKHSs using its associated integral operators and probability inequalities for random variables with values in a Hilbert space." @default.
- W2274052023 created "2016-06-24" @default.
- W2274052023 creator A5006802589 @default.
- W2274052023 creator A5048960543 @default.
- W2274052023 date "2016-04-01" @default.
- W2274052023 modified "2023-10-16" @default.
- W2274052023 title "Online Pairwise Learning Algorithms" @default.
- W2274052023 cites W1490654344 @default.
- W2274052023 cites W1970781863 @default.
- W2274052023 cites W1978810924 @default.
- W2274052023 cites W1986280275 @default.
- W2274052023 cites W1992208280 @default.
- W2274052023 cites W1994616650 @default.
- W2274052023 cites W1996652862 @default.
- W2274052023 cites W2002658919 @default.
- W2274052023 cites W2017332415 @default.
- W2274052023 cites W2022829242 @default.
- W2274052023 cites W2025199224 @default.
- W2274052023 cites W2033855314 @default.
- W2274052023 cites W2034978228 @default.
- W2274052023 cites W2047278710 @default.
- W2274052023 cites W2059571389 @default.
- W2274052023 cites W2087789467 @default.
- W2274052023 cites W2099210314 @default.
- W2274052023 cites W2109339818 @default.
- W2274052023 cites W2154558852 @default.
- W2274052023 cites W4245558064 @default.
- W2274052023 cites W4251115686 @default.
- W2274052023 cites W4253840677 @default.
- W2274052023 doi "https://doi.org/10.1162/neco_a_00817" @default.
- W2274052023 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/26890352" @default.
- W2274052023 hasPublicationYear "2016" @default.
- W2274052023 type Work @default.
- W2274052023 sameAs 2274052023 @default.
- W2274052023 citedByCount "36" @default.
- W2274052023 countsByYear W22740520232016 @default.
- W2274052023 countsByYear W22740520232017 @default.
- W2274052023 countsByYear W22740520232018 @default.
- W2274052023 countsByYear W22740520232019 @default.
- W2274052023 countsByYear W22740520232020 @default.
- W2274052023 countsByYear W22740520232021 @default.
- W2274052023 countsByYear W22740520232022 @default.
- W2274052023 countsByYear W22740520232023 @default.
- W2274052023 crossrefType "journal-article" @default.
- W2274052023 hasAuthorship W2274052023A5006802589 @default.
- W2274052023 hasAuthorship W2274052023A5048960543 @default.
- W2274052023 hasConcept C105795698 @default.
- W2274052023 hasConcept C11413529 @default.
- W2274052023 hasConcept C118615104 @default.
- W2274052023 hasConcept C12267149 @default.
- W2274052023 hasConcept C126255220 @default.
- W2274052023 hasConcept C134306372 @default.
- W2274052023 hasConcept C140479938 @default.
- W2274052023 hasConcept C154945302 @default.
- W2274052023 hasConcept C184898388 @default.
- W2274052023 hasConcept C33923547 @default.
- W2274052023 hasConcept C34388435 @default.
- W2274052023 hasConcept C39891107 @default.
- W2274052023 hasConcept C41008148 @default.
- W2274052023 hasConcept C62799726 @default.
- W2274052023 hasConcept C74193536 @default.
- W2274052023 hasConcept C80884492 @default.
- W2274052023 hasConceptScore W2274052023C105795698 @default.
- W2274052023 hasConceptScore W2274052023C11413529 @default.
- W2274052023 hasConceptScore W2274052023C118615104 @default.
- W2274052023 hasConceptScore W2274052023C12267149 @default.
- W2274052023 hasConceptScore W2274052023C126255220 @default.
- W2274052023 hasConceptScore W2274052023C134306372 @default.
- W2274052023 hasConceptScore W2274052023C140479938 @default.
- W2274052023 hasConceptScore W2274052023C154945302 @default.
- W2274052023 hasConceptScore W2274052023C184898388 @default.
- W2274052023 hasConceptScore W2274052023C33923547 @default.
- W2274052023 hasConceptScore W2274052023C34388435 @default.
- W2274052023 hasConceptScore W2274052023C39891107 @default.
- W2274052023 hasConceptScore W2274052023C41008148 @default.
- W2274052023 hasConceptScore W2274052023C62799726 @default.
- W2274052023 hasConceptScore W2274052023C74193536 @default.
- W2274052023 hasConceptScore W2274052023C80884492 @default.
- W2274052023 hasIssue "4" @default.
- W2274052023 hasLocation W22740520231 @default.
- W2274052023 hasLocation W22740520232 @default.
- W2274052023 hasOpenAccess W2274052023 @default.
- W2274052023 hasPrimaryLocation W22740520231 @default.
- W2274052023 hasRelatedWork W2158677029 @default.
- W2274052023 hasRelatedWork W2274052023 @default.
- W2274052023 hasRelatedWork W2327800007 @default.
- W2274052023 hasRelatedWork W2370340664 @default.
- W2274052023 hasRelatedWork W2374023116 @default.
- W2274052023 hasRelatedWork W2755771259 @default.
- W2274052023 hasRelatedWork W2899252297 @default.
- W2274052023 hasRelatedWork W2964176314 @default.
- W2274052023 hasRelatedWork W3037944359 @default.
- W2274052023 hasRelatedWork W3170945357 @default.
- W2274052023 hasVolume "28" @default.
- W2274052023 isParatext "false" @default.
- W2274052023 isRetracted "false" @default.
- W2274052023 magId "2274052023" @default.
- W2274052023 workType "article" @default.