Matches in SemOpenAlex for { <https://semopenalex.org/work/W2512490502> ?p ?o ?g. }
- W2512490502 endingPage "1911" @default.
- W2512490502 startingPage "1883" @default.
- W2512490502 abstract "Linear convergence rates of descent methods for unconstrained minimization are usually proved under the assumption that the objective function is strongly convex. Recently it was shown that the weaker assumption of restricted strong convexity suffices for linear convergence of the ordinary gradient descent method. A decisive difference to strong convexity is that the set of minimizers of a restricted strongly convex function need be neither a singleton nor bounded. In this paper we extend the linear convergence results under this weaker assumption to a larger class of descent methods including restarted nonlinear CG, BFGS, and its damped limited memory variants, L-D-BFGS. For twice continuously differentiable objective functions we even obtain r-step superlinear convergence for the CG_DESCENT conjugate gradient method of Hager and Zhang, where r is greater than or equal to the rank of the Hessian at a minimizer. This is remarkable since the Hessian of a restricted strongly convex function need not have full rank. Furthermore we show that convex quadratic splines and objective functions of the unconstrained duals to some linearly constrained optimization problems are restricted strongly convex. In particular this holds for the regularized basis pursuit problem and its analogues for nuclear norm minimization and principal component pursuit." @default.
- W2512490502 created "2016-09-16" @default.
- W2512490502 creator A5021686299 @default.
- W2512490502 date "2016-01-01" @default.
- W2512490502 modified "2023-09-27" @default.
- W2512490502 title "Linear Convergence of Descent Methods for the Unconstrained Minimization of Restricted Strongly Convex Functions" @default.
- W2512490502 cites W1583089965 @default.
- W2512490502 cites W1966490949 @default.
- W2512490502 cites W1969123878 @default.
- W2512490502 cites W1975017829 @default.
- W2512490502 cites W1979347641 @default.
- W2512490502 cites W1981831430 @default.
- W2512490502 cites W1984553293 @default.
- W2512490502 cites W1986931325 @default.
- W2512490502 cites W2002854334 @default.
- W2512490502 cites W2010661079 @default.
- W2512490502 cites W2012231377 @default.
- W2512490502 cites W2014851363 @default.
- W2512490502 cites W2018215034 @default.
- W2512490502 cites W2020457356 @default.
- W2512490502 cites W2025469203 @default.
- W2512490502 cites W2028372504 @default.
- W2512490502 cites W2029213856 @default.
- W2512490502 cites W2035507034 @default.
- W2512490502 cites W2045968916 @default.
- W2512490502 cites W2047391904 @default.
- W2512490502 cites W2051434435 @default.
- W2512490502 cites W2054287207 @default.
- W2512490502 cites W2054803831 @default.
- W2512490502 cites W2061127301 @default.
- W2512490502 cites W2061211758 @default.
- W2512490502 cites W2061315188 @default.
- W2512490502 cites W2062294426 @default.
- W2512490502 cites W2066743741 @default.
- W2512490502 cites W2072378378 @default.
- W2512490502 cites W2075706482 @default.
- W2512490502 cites W2075826622 @default.
- W2512490502 cites W2079482358 @default.
- W2512490502 cites W2082326665 @default.
- W2512490502 cites W2086128789 @default.
- W2512490502 cites W2090084467 @default.
- W2512490502 cites W2091549324 @default.
- W2512490502 cites W2093417350 @default.
- W2512490502 cites W2096220424 @default.
- W2512490502 cites W2101868363 @default.
- W2512490502 cites W2103972604 @default.
- W2512490502 cites W2108560279 @default.
- W2512490502 cites W2118550318 @default.
- W2512490502 cites W2145962650 @default.
- W2512490502 cites W2153532571 @default.
- W2512490502 cites W2316564661 @default.
- W2512490502 cites W2964222150 @default.
- W2512490502 cites W2964352004 @default.
- W2512490502 cites W3104624268 @default.
- W2512490502 cites W4240533965 @default.
- W2512490502 doi "https://doi.org/10.1137/140992990" @default.
- W2512490502 hasPublicationYear "2016" @default.
- W2512490502 type Work @default.
- W2512490502 sameAs 2512490502 @default.
- W2512490502 citedByCount "19" @default.
- W2512490502 countsByYear W25124905022015 @default.
- W2512490502 countsByYear W25124905022016 @default.
- W2512490502 countsByYear W25124905022018 @default.
- W2512490502 countsByYear W25124905022019 @default.
- W2512490502 countsByYear W25124905022020 @default.
- W2512490502 countsByYear W25124905022021 @default.
- W2512490502 countsByYear W25124905022022 @default.
- W2512490502 countsByYear W25124905022023 @default.
- W2512490502 crossrefType "journal-article" @default.
- W2512490502 hasAuthorship W2512490502A5021686299 @default.
- W2512490502 hasConcept C106159729 @default.
- W2512490502 hasConcept C112680207 @default.
- W2512490502 hasConcept C114614502 @default.
- W2512490502 hasConcept C119857082 @default.
- W2512490502 hasConcept C134306372 @default.
- W2512490502 hasConcept C145446738 @default.
- W2512490502 hasConcept C153258448 @default.
- W2512490502 hasConcept C162324750 @default.
- W2512490502 hasConcept C164226766 @default.
- W2512490502 hasConcept C203616005 @default.
- W2512490502 hasConcept C22324862 @default.
- W2512490502 hasConcept C2524010 @default.
- W2512490502 hasConcept C28826006 @default.
- W2512490502 hasConcept C33923547 @default.
- W2512490502 hasConcept C41008148 @default.
- W2512490502 hasConcept C50644808 @default.
- W2512490502 hasConcept C72134830 @default.
- W2512490502 hasConceptScore W2512490502C106159729 @default.
- W2512490502 hasConceptScore W2512490502C112680207 @default.
- W2512490502 hasConceptScore W2512490502C114614502 @default.
- W2512490502 hasConceptScore W2512490502C119857082 @default.
- W2512490502 hasConceptScore W2512490502C134306372 @default.
- W2512490502 hasConceptScore W2512490502C145446738 @default.
- W2512490502 hasConceptScore W2512490502C153258448 @default.
- W2512490502 hasConceptScore W2512490502C162324750 @default.
- W2512490502 hasConceptScore W2512490502C164226766 @default.
- W2512490502 hasConceptScore W2512490502C203616005 @default.
- W2512490502 hasConceptScore W2512490502C22324862 @default.