Matches in SemOpenAlex for { <https://semopenalex.org/work/W2099891036> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W2099891036 abstract "Support vector machines (SVMs) are invaluable tools for many practical applications in artificial intelligence, e.g., classification and event recognition. However, popular SVM solvers are not sufficiently efficient for applications with a great deal of samples as well as a large number of features. In this paper, thus, we present NESVM, a fast gradient SVM solver that can optimize various SVM models, e.g., classical SVM, linear programming SVM and least square SVM. Compared against SVM-Perf (whose convergence rate in solving the dual SVM is upper bounded by O(1/√k) where k is the number of iterations) and Pegasos (online SVM that converges at rate O(1/k) for the primal SVM), NESVM achieves the optimal convergence rate at O(1/k <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>2</sup> ) and a linear time complexity. In particular, NESVM smoothes the nondifferentiable hinge loss and ℓ <sub xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>1</sub> -norm in the primal SVM. Then the optimal gradient method without any line search is adopted to solve the optimization. In each iteration round, the current gradient and historical gradients are combined to determine the descent direction, while the Lipschitz constant determines the step size. Only two matrix-vector multiplications are required in each iteration round. Therefore, NESVM is more efficient than existing SVM solvers. In addition, NESVM is available for both linear and nonlinear kernels. We also propose homotopy NESVM to accelerate NESVM by dynamically decreasing the smooth parameter and using the continuation method. Our experiments on census income categorization, indoor/outdoor scene classification event recognition and scene recognition suggest the efficiency and the effectiveness of NESVM. The MATLAB code of NESVM will be available on our website for further assessment." @default.
- W2099891036 created "2016-06-24" @default.
- W2099891036 creator A5001819736 @default.
- W2099891036 creator A5039076312 @default.
- W2099891036 creator A5080738591 @default.
- W2099891036 date "2010-12-01" @default.
- W2099891036 modified "2023-09-24" @default.
- W2099891036 title "NESVM: A Fast Gradient Method for Support Vector Machines" @default.
- W2099891036 cites W1596717185 @default.
- W2099891036 cites W2007972815 @default.
- W2099891036 cites W2031248101 @default.
- W2099891036 cites W2035720976 @default.
- W2099891036 cites W2051381803 @default.
- W2099891036 cites W2064575768 @default.
- W2099891036 cites W2107034620 @default.
- W2099891036 cites W2117699623 @default.
- W2099891036 cites W2121823378 @default.
- W2099891036 cites W2142623206 @default.
- W2099891036 cites W2147625498 @default.
- W2099891036 cites W2147898188 @default.
- W2099891036 cites W2152161678 @default.
- W2099891036 cites W2156909104 @default.
- W2099891036 cites W2167732364 @default.
- W2099891036 cites W2168920183 @default.
- W2099891036 cites W2109340186 @default.
- W2099891036 doi "https://doi.org/10.1109/icdm.2010.135" @default.
- W2099891036 hasPublicationYear "2010" @default.
- W2099891036 type Work @default.
- W2099891036 sameAs 2099891036 @default.
- W2099891036 citedByCount "39" @default.
- W2099891036 countsByYear W20998910362012 @default.
- W2099891036 countsByYear W20998910362013 @default.
- W2099891036 countsByYear W20998910362014 @default.
- W2099891036 countsByYear W20998910362015 @default.
- W2099891036 countsByYear W20998910362016 @default.
- W2099891036 countsByYear W20998910362017 @default.
- W2099891036 countsByYear W20998910362018 @default.
- W2099891036 countsByYear W20998910362019 @default.
- W2099891036 countsByYear W20998910362022 @default.
- W2099891036 crossrefType "proceedings-article" @default.
- W2099891036 hasAuthorship W2099891036A5001819736 @default.
- W2099891036 hasAuthorship W2099891036A5039076312 @default.
- W2099891036 hasAuthorship W2099891036A5080738591 @default.
- W2099891036 hasBestOaLocation W20998910362 @default.
- W2099891036 hasConcept C11413529 @default.
- W2099891036 hasConcept C12267149 @default.
- W2099891036 hasConcept C124975894 @default.
- W2099891036 hasConcept C126255220 @default.
- W2099891036 hasConcept C153258448 @default.
- W2099891036 hasConcept C154945302 @default.
- W2099891036 hasConcept C162324750 @default.
- W2099891036 hasConcept C206688291 @default.
- W2099891036 hasConcept C26517878 @default.
- W2099891036 hasConcept C2777303404 @default.
- W2099891036 hasConcept C33923547 @default.
- W2099891036 hasConcept C38652104 @default.
- W2099891036 hasConcept C39891107 @default.
- W2099891036 hasConcept C41008148 @default.
- W2099891036 hasConcept C50522688 @default.
- W2099891036 hasConcept C50644808 @default.
- W2099891036 hasConcept C57869625 @default.
- W2099891036 hasConceptScore W2099891036C11413529 @default.
- W2099891036 hasConceptScore W2099891036C12267149 @default.
- W2099891036 hasConceptScore W2099891036C124975894 @default.
- W2099891036 hasConceptScore W2099891036C126255220 @default.
- W2099891036 hasConceptScore W2099891036C153258448 @default.
- W2099891036 hasConceptScore W2099891036C154945302 @default.
- W2099891036 hasConceptScore W2099891036C162324750 @default.
- W2099891036 hasConceptScore W2099891036C206688291 @default.
- W2099891036 hasConceptScore W2099891036C26517878 @default.
- W2099891036 hasConceptScore W2099891036C2777303404 @default.
- W2099891036 hasConceptScore W2099891036C33923547 @default.
- W2099891036 hasConceptScore W2099891036C38652104 @default.
- W2099891036 hasConceptScore W2099891036C39891107 @default.
- W2099891036 hasConceptScore W2099891036C41008148 @default.
- W2099891036 hasConceptScore W2099891036C50522688 @default.
- W2099891036 hasConceptScore W2099891036C50644808 @default.
- W2099891036 hasConceptScore W2099891036C57869625 @default.
- W2099891036 hasLocation W20998910361 @default.
- W2099891036 hasLocation W20998910362 @default.
- W2099891036 hasLocation W20998910363 @default.
- W2099891036 hasOpenAccess W2099891036 @default.
- W2099891036 hasPrimaryLocation W20998910361 @default.
- W2099891036 hasRelatedWork W2075181955 @default.
- W2099891036 hasRelatedWork W2099891036 @default.
- W2099891036 hasRelatedWork W2128886773 @default.
- W2099891036 hasRelatedWork W2766590049 @default.
- W2099891036 hasRelatedWork W2928207644 @default.
- W2099891036 hasRelatedWork W2972443910 @default.
- W2099891036 hasRelatedWork W3114199884 @default.
- W2099891036 hasRelatedWork W3197169288 @default.
- W2099891036 hasRelatedWork W4307415224 @default.
- W2099891036 hasRelatedWork W43388155 @default.
- W2099891036 isParatext "false" @default.
- W2099891036 isRetracted "false" @default.
- W2099891036 magId "2099891036" @default.
- W2099891036 workType "article" @default.