A family of second-order methods for convex -regularized optimization
Küçük Resim Yok
Tarih
2016
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Springer Heidelberg
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
This paper is concerned with the minimization of an objective that is the sum of a convex function f and an regularization term. Our interest is in active-set methods that incorporate second-order information about the function f to accelerate convergence. We describe a semismooth Newton framework that can be used to generate a variety of second-order methods, including block active set methods, orthant-based methods and a second-order iterative soft-thresholding method. The paper proposes a new active set method that performs multiple changes in the active manifold estimate at every iteration, and employs a mechanism for correcting these estimates, when needed. This corrective mechanism is also evaluated in an orthant-based method. Numerical tests comparing the performance of three active set methods are presented.
Açıklama
Anahtar Kelimeler
Thresholding Algorithm, Newton, Shrinkage, Strategy, Online
Kaynak
Mathematical Programming
WoS Q Değeri
Q1
Scopus Q Değeri
Q1
Cilt
159
Sayı
1.Şub
