A line-search based SGD algorithm with adaptive importance sampling

DOI10.1016/J.CAM.2025.117120MaRDI QIDQ6875718zbMATH OpenFDO

Authors Filippo Camellini, Serena Crisci, Anna De Magistris, Giorgia Franchini

Publication date 13 January 2026

Published in Journal of Computational and Applied Mathematics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.CAM.2025.117120

zbMATH Keywords

importance samplingline-searchmachine learningnonlinear optimizationstochastic gradient

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Stochastic programming (90C15) Nonlinear programming (90C30)

Cites work

• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• A line search based proximal stochastic gradient algorithm with dynamical variance reduction
• A proximal stochastic gradient method with progressive variance reduction
• A Stochastic Approximation Method
• A stochastic gradient method with variance control and variable learning rate for deep learning
• Adaptive sampling strategies for stochastic optimization
• Adaptive subgradient methods for online learning and stochastic optimization
• Convex optimization theory.
• Minimization of functions having Lipschitz continuous first partial derivatives
• Optimization methods for large-scale machine learning
• Probabilistic line searches for stochastic optimization
• Sample size selection in optimization methods for machine learning
• Spectral stochastic gradient method with additional sampling for finite and infinite sums
• Stochastic three-term conjugate gradient method with variance technique for non-convex learning

Cited in

(1)

• NAMAS-numerical analysis \& modelling in applied sciences

This page was built for publication: A line-search based SGD algorithm with adaptive importance sampling

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6875718)