On inexact stochastic splitting methods for a class of nonconvex composite optimization problems with relative error

DOI10.1080/10556788.2022.2091562OpenAlexW4286219953MaRDI QIDQ5882219

Jia Hu, Cong-Ying Han, Tong Zhao, Tian-de Guo

Publication date: 15 March 2023

Published in: Optimization Methods and Software (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/10556788.2022.2091562

zbMATH Keywords

stochastic approximationvariance reductionrelative erroralternating direction method of multipliersnonsmooth nonconvex optimizationproximal gradient descent

Mathematics Subject Classification ID

Numerical optimization and variational techniques (65K10) Applications of operator theory in optimization, convex analysis, mathematical programming, economics (47N10)

Uses Software

• SparseLOGREG
• ProxSARAH
• Saga

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Minimizing finite sums with the stochastic average gradient
• On the linear convergence of the alternating direction method of multipliers
• An extragradient-based alternating direction method for convex minimization
• A dual algorithm for the solution of nonlinear variational problems via finite element approximation
• A hybrid approximate extragradient-proximal point algorithm using the enlargement of a maximal monotone operator
• On the information-adaptive variants of the ADMM: an iteration complexity perspective
• Structured nonconvex and nonsmooth optimization: algorithms and iteration complexity analysis
• Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
• An inexact proximal generalized alternating direction method of multipliers
• On proximal subgradient splitting method for minimizing the sum of two nonsmooth convex functions
• On the $O(1/n)$ Convergence Rate of the Douglas–Rachford Alternating Direction Method
• Convergence Analysis of Alternating Direction Method of Multipliers for a Family of Nonconvex Problems
• On the Complexity of the Hybrid Proximal Extragradient Method for the Iterates and the Ergodic Mean
• Global Convergence of Splitting Methods for Nonconvex Composite Optimization
• A generalized proximal point algorithm for certain non-convex minimization problems
• Inexact Variants of the Proximal Point Algorithm without Monotonicity
• Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization I: A Generic Algorithmic Framework
• A Proximal Stochastic Gradient Method with Progressive Variance Reduction
• Iteration-Complexity of Block-Decomposition Algorithms and the Alternating Direction Method of Multipliers
• On the Global Linear Convergence of the ADMM with MultiBlock Variables
• A Stochastic Approximation Method
• Mini-batch stochastic approximation methods for nonconvex stochastic composite optimization

This page was built for publication: On inexact stochastic splitting methods for a class of nonconvex composite optimization problems with relative error