Matches in SemOpenAlex for { <https://semopenalex.org/work/W2771029897> ?p ?o ?g. }
- W2771029897 abstract "In this paper, we consider a class of possibly nonconvex, nonsmooth and non-Lipschitz optimization problems arising in many contemporary applications such as machine learning, variable selection and image processing. To solve this class of problems, we propose a proximal gradient method with extrapolation and line search (PGels). This method is developed based on a special potential function and successfully incorporates both extrapolation and non-monotone line search, which are two simple and efficient accelerating techniques for the proximal gradient method. Thanks to the line search, this method allows more flexibilities in choosing the extrapolation parameters and updates them adaptively at each iteration if a certain line search criterion is not satisfied. Moreover, with proper choices of parameters, our PGels reduces to many existing algorithms. We also show that, under some mild conditions, our line search criterion is well defined and any cluster point of the sequence generated by PGels is a stationary point of our problem. In addition, by assuming the Kurdyka-${L}$ojasiewicz exponent of the objective in our problem, we further analyze the local convergence rate of two special cases of PGels, including the widely used non-monotone proximal gradient method as one case. Finally, we conduct some numerical experiments for solving the $ell_1$ regularized logistic regression problem and the $ell_{1text{-}2}$ regularized least squares problem. Our numerical results illustrate the efficiency of PGels and show the potential advantage of combining two accelerating techniques." @default.
- W2771029897 created "2017-12-04" @default.
- W2771029897 creator A5023071921 @default.
- W2771029897 date "2017-11-18" @default.
- W2771029897 modified "2023-09-27" @default.
- W2771029897 title "Proximal Gradient Method with Extrapolation and Line Search for a Class of Nonconvex and Nonsmooth Problems" @default.
- W2771029897 cites W1546266651 @default.
- W2771029897 cites W1569098853 @default.
- W2771029897 cites W1967138577 @default.
- W2771029897 cites W1968154520 @default.
- W2771029897 cites W1968694834 @default.
- W2771029897 cites W1973734200 @default.
- W2771029897 cites W1987083649 @default.
- W2771029897 cites W2000462146 @default.
- W2771029897 cites W2004160833 @default.
- W2771029897 cites W2019569173 @default.
- W2771029897 cites W2021361347 @default.
- W2771029897 cites W2027982384 @default.
- W2771029897 cites W2030161963 @default.
- W2771029897 cites W2043430160 @default.
- W2771029897 cites W2048742402 @default.
- W2771029897 cites W2074682976 @default.
- W2771029897 cites W2078853581 @default.
- W2771029897 cites W2089106993 @default.
- W2771029897 cites W2098000549 @default.
- W2771029897 cites W2100556411 @default.
- W2771029897 cites W2101868363 @default.
- W2771029897 cites W2119058682 @default.
- W2771029897 cites W2126607811 @default.
- W2771029897 cites W2127447444 @default.
- W2771029897 cites W2129732816 @default.
- W2771029897 cites W2135046866 @default.
- W2771029897 cites W2142224912 @default.
- W2771029897 cites W2166388529 @default.
- W2771029897 cites W2167137033 @default.
- W2771029897 cites W2184634347 @default.
- W2771029897 cites W2405803404 @default.
- W2771029897 cites W2576873436 @default.
- W2771029897 cites W2616806001 @default.
- W2771029897 cites W2727634334 @default.
- W2771029897 cites W2743133559 @default.
- W2771029897 cites W2796619875 @default.
- W2771029897 cites W2962871487 @default.
- W2771029897 cites W2963118312 @default.
- W2771029897 cites W2963264932 @default.
- W2771029897 cites W2963373709 @default.
- W2771029897 cites W2963375486 @default.
- W2771029897 cites W2963648037 @default.
- W2771029897 cites W2963906098 @default.
- W2771029897 cites W3100208521 @default.
- W2771029897 cites W3141595720 @default.
- W2771029897 doi "https://doi.org/10.48550/arxiv.1711.06831" @default.
- W2771029897 hasPublicationYear "2017" @default.
- W2771029897 type Work @default.
- W2771029897 sameAs 2771029897 @default.
- W2771029897 citedByCount "2" @default.
- W2771029897 countsByYear W27710298972018 @default.
- W2771029897 countsByYear W27710298972019 @default.
- W2771029897 crossrefType "posted-content" @default.
- W2771029897 hasAuthorship W2771029897A5023071921 @default.
- W2771029897 hasBestOaLocation W27710298971 @default.
- W2771029897 hasConcept C10494615 @default.
- W2771029897 hasConcept C112680207 @default.
- W2771029897 hasConcept C11413529 @default.
- W2771029897 hasConcept C126255220 @default.
- W2771029897 hasConcept C127162648 @default.
- W2771029897 hasConcept C132459708 @default.
- W2771029897 hasConcept C134306372 @default.
- W2771029897 hasConcept C145446738 @default.
- W2771029897 hasConcept C178635117 @default.
- W2771029897 hasConcept C198352243 @default.
- W2771029897 hasConcept C22324862 @default.
- W2771029897 hasConcept C2524010 @default.
- W2771029897 hasConcept C2834757 @default.
- W2771029897 hasConcept C28719098 @default.
- W2771029897 hasConcept C28826006 @default.
- W2771029897 hasConcept C31258907 @default.
- W2771029897 hasConcept C33923547 @default.
- W2771029897 hasConcept C38652104 @default.
- W2771029897 hasConcept C41008148 @default.
- W2771029897 hasConcept C57869625 @default.
- W2771029897 hasConcept C85522705 @default.
- W2771029897 hasConceptScore W2771029897C10494615 @default.
- W2771029897 hasConceptScore W2771029897C112680207 @default.
- W2771029897 hasConceptScore W2771029897C11413529 @default.
- W2771029897 hasConceptScore W2771029897C126255220 @default.
- W2771029897 hasConceptScore W2771029897C127162648 @default.
- W2771029897 hasConceptScore W2771029897C132459708 @default.
- W2771029897 hasConceptScore W2771029897C134306372 @default.
- W2771029897 hasConceptScore W2771029897C145446738 @default.
- W2771029897 hasConceptScore W2771029897C178635117 @default.
- W2771029897 hasConceptScore W2771029897C198352243 @default.
- W2771029897 hasConceptScore W2771029897C22324862 @default.
- W2771029897 hasConceptScore W2771029897C2524010 @default.
- W2771029897 hasConceptScore W2771029897C2834757 @default.
- W2771029897 hasConceptScore W2771029897C28719098 @default.
- W2771029897 hasConceptScore W2771029897C28826006 @default.
- W2771029897 hasConceptScore W2771029897C31258907 @default.
- W2771029897 hasConceptScore W2771029897C33923547 @default.
- W2771029897 hasConceptScore W2771029897C38652104 @default.