An adaptive stochastic gradient descent algorithm for solving convex optimization problenms

DOI10.12286/JSSX.J2025-1351MaRDI QIDQ7320124zbMATH OpenFDO

Authors Tianhui Yu, X. J. Long

Publication date 27 August 2026

Published in Mathematica Numerica Sinica (Search for Journal in Brave)

Full work available at URL https://doi.org/10.12286/JSSX.J2025-1351

Mathematics Subject Classification ID

Singular perturbations for ordinary differential equations (34E15) Boundary value problems for functional-differential equations (34K10) Numerical analysis (65-XX)

Cites work

• A novel stepsize for gradient descent method
• A proximal stochastic gradient method with progressive variance reduction
• A Stochastic Approximation Method
• Accelerated stochastic variance reduction for a class of convex optimization problems
• AdaBB: adaptive Barzilai-Borwein method for convex optimization
• Analysis and improvement for a class of variance reduced methods
• Analysis of a new BFGS algorithm and conjugate gradient algorithms and their applications in image restoration and machine learning
• Improving the stochastically controlled stochastic gradient method by the bandwidth-based stepsize
• Lectures on convex optimization
• Minimizing finite sums with the stochastic average gradient
• Non-asymptotic analysis of hybrid SPG for non-convex stochastic composite optimization
• Optimization methods for large-scale machine learning
• Robust Stochastic Approximation Approach to Stochastic Programming
• Stabilized Barzilai-Borwein method
• Two-Point Step Size Gradient Methods

This page was built for publication: An adaptive stochastic gradient descent algorithm for solving convex optimization problenms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7320124)