A heuristic adaptive fast gradient method in stochastic optimization problems

DOI10.1134/S0965542520070088zbMath1451.90107arXiv1910.04825OpenAlexW3047998707MaRDI QIDQ2207619

A. I. Tyurin, A. V. Ogal'tsov

Publication date: 23 October 2020

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

Full work available at URL: https://arxiv.org/abs/1910.04825

zbMATH Keywords

stochastic optimizationadaptive optimizationfast gradient descent

Mathematics Subject Classification ID

Stochastic programming (90C15) Methods of reduced gradient type (90C52)

Related Items (1)

Adaptive Gradient-Free Method for Stochastic Optimization

Uses Software

• CIFAR
• ImageNet
• AdaGrad
• Adam
• AlexNet

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• First-order methods of smooth convex optimization with inexact oracle
• Validation analysis of mirror descent stochastic approximation method
• Symmetrization approach to concentration inequalities for empirical processes.
• Fast gradient descent for convex minimization problems with an oracle producing a \(( \delta, L)\)-model of function at the requested point
• Variance-Based Extragradient Methods with Line Search for Stochastic Variational Inequalities

This page was built for publication: A heuristic adaptive fast gradient method in stochastic optimization problems