Semistability of Steepest Descent with Momentum for Quadratic Functions

DOI10.1162/NECO_a_00436zbMath1414.68089WikidataQ50755341 ScholiaQ50755341MaRDI QIDQ5378217

Naimin Zhang

Publication date: 12 June 2019

Published in: Neural Computation (Search for Journal in Brave)

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items

Dealing with multi-modality using synthesis of moth-flame optimizer with sine cosine mechanisms, Momentum acceleration-based matrix splitting method for solving generalized absolute value equation, A Study on the Optimal Double Parameters for Steepest Descent with Momentum, On parameter acceleration methods for saddle point problems

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• An online gradient method with momentum for two-layer feedforward neural networks
• Preconditioned conjugate gradients for solving singular systems
• Necessary and sufficient conditions for the convergence of \(\text{Orthomin}(k)\) on singular and inconsistent linear systems
• Steepest descent with momentum for quadratic functions is a version of the conjugate gradient method
• Practical selection of SVM parameters and noise estimation for SVM regression
• Numerical Optimization
• Learning representations by back-propagating errors
• On the Location of Zeros of Certain Classes of Polynomials with Applications to Numerical Analysis