Near optimal step size and momentum in gradient descent for quadratic functions

DOI10.3906/mat-1411-51zbMath1424.90200OpenAlexW2578906089MaRDI QIDQ4633246

Memmedağa Memmedli, Engin Tas

Publication date: 2 May 2019

Published in: TURKISH JOURNAL OF MATHEMATICS (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.3906/mat-1411-51

zbMATH Keywords

stabilitymomentumconvergence speedgradient descentstep size

Mathematics Subject Classification ID

Quadratic programming (90C20)

Cites Work

• Unnamed Item
• Unnamed Item
• Steepest descent with momentum for quadratic functions is a version of the conjugate gradient method
• Large-Scale Machine Learning with Stochastic Gradient Descent
• Randomly Generated Test Problems for Positive Definite Quadratic Programming
• Accelerating backpropagation using effective parameters at each step and an experimental evaluation
• Acceleration of Stochastic Approximation by Averaging