Non-monotone Behavior of the Heavy Ball Method

DOI10.1007/978-3-030-35502-9_9zbMath1445.39002arXiv1811.00658OpenAlexW3104949911MaRDI QIDQ3296870

Marina Danilova, Anastasiia Kulakova, Boris T. Polyak

Publication date: 2 July 2020

Published in: Springer Proceedings in Mathematics & Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1811.00658

zbMATH Keywords

global convergenceLyapunov functiondifference equationsoptimization methodsnon-monotone behaviorheavy ball method

Mathematics Subject Classification ID

Growth, boundedness, comparison of solutions to difference equations (39A22) Stability theory for difference equations (39A30) Linear difference equations (39A06)

Related Items

A probabilistic point of view on peak effects in linear difference equations

Cites Work

• Universal gradient methods for convex optimization problems
• Introductory lectures on convex optimization. A basic course.
• Adaptive restart of the optimized gradient method for convex optimization
• Adaptive restart for accelerated gradient schemes
• Peak effects in stable linear difference equations
• Some methods of speeding up the convergence of iteration methods
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item