A modified generalized version of projected reflected gradient method in Hilbert spaces

Zhou, Xiaolin; Cai, Gang; Tan, Bing; Dong, Qiao-Li

doi:10.1007/s11075-023-01566-1

Numer Algor

2023

DOI: 10.1007/s11075-023-01566-1

|View full text |Cite

A modified generalized version of projected reflected gradient method in Hilbert spaces

Xiaolin Zhou

Gang Cai

Bing Tan

et al.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

Publication Types

Select...

Article1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

MAMGD: Gradient-Based Optimization Method Using Exponential Decay

Sakovich,

Aksenov,

Pleshakova

et al. 2024

Technologies

View full text Add to dashboard Cite

Optimization methods, namely, gradient optimization methods, are a key part of neural network training. In this paper, we propose a new gradient optimization method using exponential decay and the adaptive learning rate using a discrete second-order derivative of gradients. The MAMGD optimizer uses an adaptive learning step, exponential smoothing and gradient accumulation, parameter correction, and some discrete analogies from classical mechanics. The experiments included minimization of multivariate real functions, function approximation using multilayer neural networks, and training neural networks on popular classification and regression datasets. The experimental results of the new optimization technology showed a high convergence speed, stability to fluctuations, and an accumulation of gradient accumulators. The research methodology is based on the quantitative performance analysis of the algorithm by conducting computational experiments on various optimization problems and comparing it with existing methods.

show abstract

MAMGD: Gradient-Based Optimization Method Using Exponential Decay

Sakovich,

Aksenov,

Pleshakova

et al. 2024

Technologies

View full text Add to dashboard Cite

show abstract

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

customersupport@researchsolutions.com

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

A modified generalized version of projected reflected gradient method in Hilbert spaces

Cited by 1 publication

References 28 publications

MAMGD: Gradient-Based Optimization Method Using Exponential Decay

MAMGD: Gradient-Based Optimization Method Using Exponential Decay

Contact Info

Product

Resources

About