Articles liés à A Coordinate Gradient Descent Method for Structured...
A Coordinate Gradient Descent Method for Structured Nonsmooth Optimization: Theory and Applications - Couverture souple
Synopsis
Nonsmooth optimization problems are generally considered to be more difficult than smooth problems. Yet, there is an important class of nonsmooth problems that lie in between. In this book, we consider the problem of minimizing the sum of a smooth function and a (block separable) convex function with or without linear constraints. This problem includes as special cases bound-constrained optimization, smooth optimization with L_1-regularization, and linearly constrained smooth optimization such as a large-scale quadratic programming problem arising in the training of support vector machines. We propose a block coordinate gradient descent method for solving this class of structured nonsmooth problems. The method is simple, highly parallelizable, and suited for large-scale applications in signal/image denoising, regression, and data mining/classification. We establish global convergence and, under a local Lipschitzian error bound assumption, local linear rate of convergence for this method. Our numerical experiences suggest that our method is effective in practice. This book is helpful to the people who are interested in solving large-scale optimization problems.
Les informations fournies dans la section « Synopsis » peuvent faire référence à une autre édition de ce titre.
À propos de l?auteur
Sangwoon Yun: PhD in Mathematics at University of Washington. Research interest: Convex and nonsmooth optimization, variational analysis. Research Fellow at National University of Singapore.
Les informations fournies dans la section « A propos du livre » peuvent faire référence à une autre édition de ce titre.
Acheter neuf
Afficher cet article
EUR 39,24
EUR 9,70 expédition depuis Allemagne vers France
Destinations, frais et délaisRésultats de recherche pour A Coordinate Gradient Descent Method for Structured...
Image fournie par le vendeur
A Coordinate Gradient Descent Method for Structured Nonsmooth Optimization
Edité par
VDM Verlag Dr. Müller, 2010
ISBN 10 : 3836478609
ISBN 13 : 9783836478601
Neuf
Kartoniert / Broschiert
Vendeur : moluna, Greven, Allemagne
Évaluation du vendeur 5 sur 5 étoiles
Kartoniert / Broschiert. Etat : New. Dieser Artikel ist ein Print on Demand Artikel und wird nach Ihrer Bestellung fuer Sie gedruckt. Autor/Autorin: Yun SangwoonSangwoon Yun: PhD in Mathematics at University of Washington. Research interest: Convex and nonsmooth optimization, variational analysis. Research Fellow at National University of Singapore.Nonsmooth optimization pr. N° de réf. du vendeur 5388240
Quantité disponible : Plus de 20 disponibles
Image fournie par le vendeur
A Coordinate Gradient Descent Method for Structured Nonsmooth Optimization : Theory and Applications
Edité par
VDM Verlag Dr. Müller E.K., 2010
ISBN 10 : 3836478609
ISBN 13 : 9783836478601
Neuf
Taschenbuch
Vendeur : AHA-BUCH GmbH, Einbeck, Allemagne
Évaluation du vendeur 5 sur 5 étoiles
Taschenbuch. Etat : Neu. nach der Bestellung gedruckt Neuware - Printed after ordering - Nonsmooth optimization problems are generally considered to be more difficult than smooth problems. Yet, there is an important class of nonsmooth problems that lie in between. In this book, we consider the problem of minimizing the sum of a smooth function and a (block separable) convex function with or without linear constraints. This problem includes as special cases bound-constrained optimization, smooth optimization with L_1-regularization, and linearly constrained smooth optimization such as a large-scale quadratic programming problem arising in the training of support vector machines. We propose a block coordinate gradient descent method for solving this class of structured nonsmooth problems. The method is simple, highly parallelizable, and suited for large-scale applications in signal/image denoising, regression, and data mining/classification. We establish global convergence and, under a local Lipschitzian error bound assumption, local linear rate of convergence for this method. Our numerical experiences suggest that our method is effective in practice. This book is helpful to the people who are interested in solving large-scale optimization problems. N° de réf. du vendeur 9783836478601
Quantité disponible : 1 disponible(s)
Image fournie par le vendeur
A Coordinate Gradient Descent Method for Structured Nonsmooth Optimization
Edité par
VDM Verlag Dr. Müller E.K. Nov 2012, 2012
ISBN 10 : 3836478609
ISBN 13 : 9783836478601
Neuf
Taschenbuch
Vendeur : BuchWeltWeit Ludwig Meier e.K., Bergisch Gladbach, Allemagne
Évaluation du vendeur 5 sur 5 étoiles
Taschenbuch. Etat : Neu. This item is printed on demand - it takes 3-4 days longer - Neuware -Nonsmooth optimization problems are generally considered to be more difficult than smooth problems. Yet, there is an important class of nonsmooth problems that lie in between. In this book, we consider the problem of minimizing the sum of a smooth function and a (block separable) convex function with or without linear constraints. This problem includes as special cases bound-constrained optimization, smooth optimization with L_1-regularization, and linearly constrained smooth optimization such as a large-scale quadratic programming problem arising in the training of support vector machines. We propose a block coordinate gradient descent method for solving this class of structured nonsmooth problems. The method is simple, highly parallelizable, and suited for large-scale applications in signal/image denoising, regression, and data mining/classification. We establish global convergence and, under a local Lipschitzian error bound assumption, local linear rate of convergence for this method. Our numerical experiences suggest that our method is effective in practice. This book is helpful to the people who are interested in solving large-scale optimization problems. 112 pp. Englisch. N° de réf. du vendeur 9783836478601
Quantité disponible : 2 disponible(s)
Image fournie par le vendeur
A Coordinate Gradient Descent Method for Structured Nonsmooth Optimization
Edité par
VDM Verlag Dr. Müller E.K. Nov 2012, 2012
ISBN 10 : 3836478609
ISBN 13 : 9783836478601
Neuf
Taschenbuch
Vendeur : buchversandmimpf2000, Emtmannsberg, BAYE, Allemagne
Évaluation du vendeur 5 sur 5 étoiles
Taschenbuch. Etat : Neu. Neuware -Nonsmooth optimization problems are generally considered to be more difficult than smooth problems. Yet, there is an important class of nonsmooth problems that lie in between. In this book, we consider the problem of minimizing the sum of a smooth function and a (block separable) convex function with or without linear constraints. This problem includes as special cases bound-constrained optimization, smooth optimization with L_1-regularization, and linearly constrained smooth optimization such as a large-scale quadratic programming problem arising in the training of support vector machines. We propose a block coordinate gradient descent method for solving this class of structured nonsmooth problems. The method is simple, highly parallelizable, and suited for large-scale applications in signal/image denoising, regression, and data mining/classification. We establish global convergence and, under a local Lipschitzian error bound assumption, local linear rate of convergence for this method. Our numerical experiences suggest that our method is effective in practice. This book is helpful to the people who are interested in solving large-scale optimization problems.VDM Verlag, Dudweiler Landstraße 99, 66123 Saarbrücken 112 pp. Englisch. N° de réf. du vendeur 9783836478601
Quantité disponible : 2 disponible(s)
Image d'archives
A Coordinate Gradient Descent Method for Structured Nonsmooth Optimization
Edité par
Vdm Verlag Dr Mueller E K, 2008
ISBN 10 : 3836478609
ISBN 13 : 9783836478601
Neuf
Paperback
Vendeur : Revaluation Books, Exeter, Royaume-Uni
Évaluation du vendeur 5 sur 5 étoiles
Paperback. Etat : Brand New. 112 pages. 8.66x5.91x0.26 inches. In Stock. N° de réf. du vendeur 3836478609
Quantité disponible : 1 disponible(s)