CONVERGENCE PROPERTIES OF PROXIMAL (SUB)GRADIENT METHODS WITHOUT CONVEXITY OR SMOOTHNESS OF ANY OF THE FUNCTIONS

被引：0

作者：

Solodov, Mikhail, V ^{[1
]}

机构：

[1] IMPA Inst Matemat Pura & Aplicada, Estrada Dona Castronia, BR-22460320 Rio De Janeiro, RJ, Brazil

来源：

SIAM JOURNAL ON OPTIMIZATION | 2025年 / 35卷 / 01期

关键词：

proximal gradient methods; incremental methods; nonsmooth nonconvex optimization; MINIMIZATION; OPTIMIZATION; ALGORITHMS; NONCONVEX;

D O I：

10.1137/23M1592158

中图分类号：

O29 [应用数学];

学科分类号：

070104 ;

摘要：

We establish convergence properties for a framework that includes a variety of proximal subgradient methods, where none of the involved functions needs to be convex or differentiable. The functions are assumed to be Clarke-regular. Our results cover the projected and conditional variants for the constrained case, the use of the inertial/momentum terms, and incremental methods when each of the functions is itself a sum, and the methods process the components in this sum separately.

引用

页码：28 / 41

页数：14

共 50 条

[21] On the convergence of adaptive first order methods: proximal gradient and alternating minimization algorithms
Latafat, Puya
Themelis, Andreas
Patrinos, Panagiotis
6TH ANNUAL LEARNING FOR DYNAMICS & CONTROL CONFERENCE, 2024, 242 : 197 - 208
[22] GLOBAL CONVERGENCE PROPERTIES OF CONJUGATE GRADIENT METHODS FOR OPTIMIZATION
Gilbert, Jean Charles
Nocedal, Jorge
SIAM JOURNAL ON OPTIMIZATION, 1992, 2 (01) : 21 - 42
[23] Convergence rate analysis of proximal gradient methods with applications to composite minimization problems
Sahu, D. R.
Yao, J. C.
Verma, M.
Shukla, K. K.
OPTIMIZATION, 2021, 70 (01) : 75 - 100
[24] The convergence properties of some new conjugate gradient methods
Wei, Zengxin
Yao, Shengwei
Liu, Liying
APPLIED MATHEMATICS AND COMPUTATION, 2006, 183 (02) : 1341 - 1350
[25] Convergence properties of nonmonotone spectral projected gradient methods
Wang, CY
Liu, Q
Yang, XM
JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS, 2005, 182 (01) : 51 - 66
[26] Convergence properties of a class of nonlinear conjugate gradient methods
Liu, Jinkui
COMPUTERS & OPERATIONS RESEARCH, 2013, 40 (11) : 2656 - 2661
[27] CONVERGENCE PROPERTIES OF THE DEPENDENT PRP CONJUGATE GRADIENT METHODS
Shujun LIAN Department of Mathematics
College of Operations and Management
Journal of Systems Science & Complexity, 2006, (02) : 288 - 296
[28] Convergence properties of the dependent PRP conjugate gradient methods
Lian S.
Wang C.
Cao L.
Journal of Systems Science and Complexity, 2006, 19 (2) : 288 - 296
[29] Constant Nullspace Strong Convexity and Fast Convergence of Proximal Methods under High-Dimensional Settings
Yen, Ian E. H.
Hsieh, Cho-Jui
Ravikumar, Pradeep
Dhillon, Inderjit
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 27 (NIPS 2014), 2014, 27
[30] Parallel proximal point methods for systems of vector optimization problems on Hadamard manifolds without convexity
Ceng, L. C.
Li, X.
Qin, X.
OPTIMIZATION, 2020, 69 (02) : 357 - 383

← 1 2 3 4 5 →