Two-point step size gradient method for solving a deep learning problem

DOI10.1007/S10598-019-09468-5MaRDI QIDQ2190628zbMATH OpenOpenAlexWikidataFDO

Authors G. S. Tsanev, Todor D. Todorov

Publication date 19 June 2020

Published in Computational Mathematics and Modeling (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10598-019-09468-5

zbMATH Keywords

deep Boltzmann machinegradient iterative methodsmean-field approximation

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Recommendations

• scientific article; zbMATH DE number 5524483
• Two novel gradient methods with optimal step sizes
• Two-Point Step Size Gradient Methods
• Gradient methods with adaptive step-sizes
• Analysis of the Barzilai-Borwein step-sizes for problems in Hilbert spaces

Cites work

• An efficient learning procedure for deep Boltzmann machines
• Boltzmann Machine and Mean-Field Approximation for Structured Sparse Decompositions
• Dirichlet problem for a nonlocal p-Laplacian elliptic equation
• Finite element approximations of solutions to p-harmonic equation with dirichlet data
• scientific article; zbMATH DE number 6378127 (Why is no real title available?)
• Multimodal learning with deep Boltzmann machines
• Nonlocal problem for a general second-order elliptic operator
• On the Barzilai and Borwein choice of steplength for the gradient method
• Optimization methods for large-scale machine learning
• Two-Point Step Size Gradient Methods

Cited in

(1)

• Adaptive cyclic gradient methods with interpolation

This page was built for publication: Two-point step size gradient method for solving a deep learning problem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2190628)