A mini-batch proximal stochastic recursive gradient algorithm with diagonal Barzilai-Borwein stepsize

DOI10.1007/S40305-022-00436-2MaRDI QIDQ6097380zbMATH OpenFDO

Authors Tengteng Yu, Xinwei Liu, Yuhong Dai, Jie Sun

Publication date 5 June 2023

Published in Journal of the Operations Research Society of China (Search for Journal in Brave)

zbMATH Keywords

Barzilai-Borwein methodcomposite optimizationproximal gradient algorithmstochastic recursive gradient

Mathematics Subject Classification ID

Convex programming (90C25) Large-scale problems in mathematical programming (90C06) Applications of mathematical programming (90C90) Nonlinear programming (90C30)

Recommendations

• Stochastic gradient method with Barzilai-Borwein step for unconstrained nonlinear optimization
• Accelerating mini-batch SARAH by step size rules
• Variable metric proximal stochastic variance reduced gradient methods for nonconvex nonsmooth optimization
• A stochastic variance reduced gradient method with adaptive step for stochastic optimization
• A proximal stochastic gradient method with progressive variance reduction

Cites work

• scientific article; zbMATH DE number 7255141 (Why is no real title available?)
• scientific article; zbMATH DE number 2221955 (Why is no real title available?)
• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• A Stochastic Approximation Method
• A family of spectral gradient methods for optimization
• A linearly convergent stochastic recursive gradient method for convex optimization
• A proximal stochastic gradient method with progressive variance reduction
• An inexact accelerated stochastic ADMM for separable convex optimization
• An optimal method for stochastic composite optimization
• Deep learning
• First-order methods in optimization
• Inexact proximal stochastic gradient method for convex composite optimization
• Minimizing finite sums with the stochastic average gradient
• Optimization methods for large-scale machine learning
• Parallel stochastic gradient algorithms for large-scale matrix completion
• Stochastic proximal quasi-Newton methods for non-convex composite optimization
• Stochastic variance reduced gradient methods using a trust-region-like scheme
• The restricted strong convexity revisited: analysis of equivalence to error bound and quadratic growth
• Two-Point Step Size Gradient Methods
• Understanding machine learning. From theory to algorithms
• Variable metric proximal stochastic variance reduced gradient methods for nonconvex nonsmooth optimization

Cited in

(2)

• An adaptive projection algorithm for solving nonlinear monotone equations with convex constraints
• Stochastic gradient descent with Barzilai-Borwein update step for SVM

This page was built for publication: A mini-batch proximal stochastic recursive gradient algorithm with diagonal Barzilai-Borwein stepsize

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6097380)