A stochastic variance reduction algorithm with Bregman distances for structured composite problems

DOI10.1080/02331934.2022.2027413zbMath1519.90140arXiv2103.08822MaRDI QIDQ6106321

Van-Dung Nguyen, Băng Công Vũ

Publication date: 27 June 2023

Published in: Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2103.08822

zbMATH Keywords

stochastic optimization; linear convergence; variance reduction; primal-dual algorithm; ergodic convergence; Bregman distance; reflected method

Mathematics Subject Classification ID

90C25: Convex programming

65K10: Numerical optimization and variational techniques

90C15: Stochastic programming

65Y20: Complexity and performance of numerical algorithms

Cites Work

• Unnamed Item
• On the ergodic convergence rates of a first-order primal-dual algorithm
• Primal-dual splitting algorithm for solving inclusions with mixtures of composite, Lipschitzian, and parallel-sum type monotone operators
• A reflected forward-backward splitting method for monotone inclusions involving Lipschitzian operators
• A simple algorithm for a class of nonsmooth convex-concave saddle-point problems
• A splitting algorithm for dual monotone inclusions involving cocoercive operators
• Bregman forward-backward operator splitting
• Convergence analysis for a primal-dual monotone + skew splitting algorithm with applications to total variation minimization
• Finding the forward-Douglas-Rachford-forward method
• On the convergence rate improvement of a primal-dual splitting algorithm for solving monotone inclusion problems
• Forward-backward splitting with Bregman distances
• Accelerated randomized mirror descent algorithms for composite non-strongly convex optimization
• A stochastic inertial forward–backward splitting algorithm for multivariate monotone inclusions
• Stochastic Approximations and Perturbations in Forward-Backward Splitting for Monotone Operators
• Stochastic Block Mirror Descent Methods for Nonsmooth and Stochastic Optimization
• Convergence Analysis of a Proximal-Like Minimization Algorithm Using Bregman Functions
• Robust Stochastic Approximation Approach to Stochastic Programming
• Bregman Monotone Optimization Algorithms
• ESSENTIAL SMOOTHNESS, ESSENTIAL STRICT CONVEXITY, AND LEGENDRE FUNCTIONS IN BANACH SPACES
• Relatively Smooth Convex Optimization by First-Order Methods, and Applications
• Inducing strong convergence into the asymptotic behaviour of proximal splitting algorithms in Hilbert spaces
• A Primal-Dual Algorithm with Line Search for General Convex-Concave Saddle Point Problems
• Reflected three-operator splitting method for monotone inclusion problem
• Solving variational inequalities with Stochastic Mirror-Prox algorithm
• Optimal Primal-Dual Methods for a Class of Saddle Point Problems
• A Proximal Stochastic Gradient Method with Progressive Variance Reduction
• A First-Order Stochastic Primal-Dual Algorithm with Correction Step
• Analysis of Online Composite Mirror Descent Algorithm
• A Douglas--Rachford Type Primal-Dual Method for Solving Inclusions with Mixtures of Composite and Parallel-Sum Type Monotone Operators