Stochastic perturbation of subgradient algorithm for nonconvex deep neural networks

DOI10.1007/s40314-023-02307-9OpenAlexW4367603340MaRDI QIDQ6161107

Abdelkrim El Mouatasim, Rachid Ellaia, Eduardo Souza de Cursi

Publication date: 2 June 2023

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

Full work available at URL: https://doi.org/10.1007/s40314-023-02307-9

zbMATH Keywords

image classificationstochastic perturbationnonconvex nonsmooth optimizationsubgradient algorithmlearning ratedeep neural networks and CNN

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Nonconvex programming, global optimization (90C26) Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Subgradient method for nonconvex nonsmooth optimization
• Stochastic perturbation of reduced gradient \& GRG methods for nonconvex programming problems
• New variable-metric algorithms for nondifferentiable optimization problems
• Global optimization by random perturbation of the gradient method with a fixed parameter
• Implementation of reduced gradient with bisection algorithms for non-convex optimization problem via stochastic perturbation
• Backtracking gradient descent method and some applications in large scale optimisation. II: Algorithms and experiments
• An efficient gradient method with approximately optimal stepsize based on tensor model for unconstrained optimization
• Random perturbation of the projected variable metric method for nonsmooth nonconvex optimization problems with linear constraints
• Learning Deep Architectures for AI
• MultiComposite Nonconvex Optimization for Training Deep Neural Networks