Composite convex optimization with global and local inexact oracles

We introduce new global and local inexact oracle concepts for a wide class of convex functions in composite convex minimization. Such inexact oracles naturally arise in many situations, including primal–dual frameworks, barrier smoothing, and inexact evaluations of gradients and Hessians. We also pr...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Computational optimization and applications Ročník 76; číslo 1; s. 69 - 124
Hlavní autoři:	Sun, Tianxiao, Necoara, Ion, Tran-Dinh, Quoc
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York Springer US 01.05.2020 Springer Nature B.V
Témata:	Algorithms Computational geometry Convergence Convex analysis Convex and Discrete Geometry Convexity Linear operators Management Science Mathematics Mathematics and Statistics Operations Research Operations Research/Decision Theory Operators (mathematics) Optimization Statistics Composite convex minimization Inexact proximal Newton-type method 90C25 Self-concordant functions 90-08 Local and global inexact oracles Primal–dual second-order method
ISSN:	0926-6003, 1573-2894
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	We introduce new global and local inexact oracle concepts for a wide class of convex functions in composite convex minimization. Such inexact oracles naturally arise in many situations, including primal–dual frameworks, barrier smoothing, and inexact evaluations of gradients and Hessians. We also provide examples showing that the class of convex functions equipped with the newly inexact oracles is larger than standard self-concordant and Lipschitz gradient function classes. Further, we investigate several properties of convex and/or self-concordant functions under our inexact oracles which are useful for algorithmic development. Next, we apply our theory to develop inexact proximal Newton-type schemes for minimizing general composite convex optimization problems equipped with such inexact oracles. Our theoretical results consist of new optimization algorithms accompanied with global convergence guarantees to solve a wide class of composite convex optimization problems. When the first objective term is additionally self-concordant, we establish different local convergence results for our method. In particular, we prove that depending on the choice of accuracy levels of the inexact second-order oracles, we obtain different local convergence rates ranging from linear and superlinear to quadratic. In special cases, where convergence bounds are known, our theory recovers the best known rates. We also apply our settings to derive a new primal–dual method for composite convex minimization problems involving linear operators. Finally, we present some representative numerical examples to illustrate the benefit of the new algorithms.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ISSN:	0926-6003 1573-2894
DOI:	10.1007/s10589-020-00174-2