On the steplength selection in stochastic gradient methods

DOI10.1007/978-3-030-39081-5_17MaRDI QIDQ2200338zbMATH OpenOpenAlexFDO

Authors Giorgia Franchini, V. Ruggiero, Luca Zanni

Publication date 21 September 2020

Full work available at URL https://doi.org/10.1007/978-3-030-39081-5_17

zbMATH Keywords

machine learningRitz-like valuessteplength selection rulestochastic gradient methods

Mathematics Subject Classification ID

Numerical analysis (65-XX)

Cited in

(5)

• Asymptotic bias of stochastic gradient search
• Ritz-like values in steplength selections for stochastic gradient methods
• Analysis of practical step size selection in stochastic approximation algorithms
• Extending the Step-Size Restriction for Gradient Descent to Avoid Strict Saddle Points
• On the Barzilai and Borwein choice of steplength for the gradient method

This page was built for publication: On the steplength selection in stochastic gradient methods

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2200338)