View in EDS

An optimizer derived from Halpern's method for enhanced neural network convergence and reduced carbon emissions.

Saved in:
Bibliographic Details
Title: An optimizer derived from Halpern's method for enhanced neural network convergence and reduced carbon emissions.
Authors: Colao, Vittorio1 (AUTHOR) vittorio.colao@unical.it, Foglia, Katherine Rossella1 (AUTHOR) katherine.foglia@unical.it, Giordano, Andrea2 (AUTHOR) andrea.giordano@icar.cnr.it, Ritacco, Ettore3 (AUTHOR) ettore.ritacco@uniud.it, Spataro, William1 (AUTHOR) william.spataro@unical.it
Source: Journal of Intelligent Information Systems. Feb2026, Vol. 64 Issue 1, p77-96. 20p.
Subjects: Optimizers (Computer software), Carbon emissions, Energy consumption, Optimization algorithms, Mathematical optimization, Iterative methods (Mathematics)
Abstract: This work examines the Halpern's iterative method as a means to create new neural network optimizers that could surpass many current existing approaches. We introduce HalpernSGD, an innovative network optimizer that leverages Halpern's technique to enhance the rate of convergence of the Stochastic Gradient Descent (SGD), leading to reduced carbon emissions in neural network training processes. The combination of Halpern's iterative method and Gradient Descent (GD) has led to an algorithm with a quadratic rate of convergence compared to the simple GD. Experimental comparisons between their stochastic versions show that HalpernSGD achieves greater efficiency than SGD by requiring fewer training epochs, thus reducing energy consumption and carbon footprint while maintaining model accuracy. We also compare HalpernSGD with ADAM, identifying potential improvements to ADAM's approach in terms of stability and convergence, and suggesting a future direction for the development of combined optimizers. The implementation for HalpernSGD can be accessed at: https://github.com/EttoreRitacco/HalpernSGD.git [ABSTRACT FROM AUTHOR]
Copyright of Journal of Intelligent Information Systems is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract:This work examines the Halpern's iterative method as a means to create new neural network optimizers that could surpass many current existing approaches. We introduce HalpernSGD, an innovative network optimizer that leverages Halpern's technique to enhance the rate of convergence of the Stochastic Gradient Descent (SGD), leading to reduced carbon emissions in neural network training processes. The combination of Halpern's iterative method and Gradient Descent (GD) has led to an algorithm with a quadratic rate of convergence compared to the simple GD. Experimental comparisons between their stochastic versions show that HalpernSGD achieves greater efficiency than SGD by requiring fewer training epochs, thus reducing energy consumption and carbon footprint while maintaining model accuracy. We also compare HalpernSGD with ADAM, identifying potential improvements to ADAM's approach in terms of stability and convergence, and suggesting a future direction for the development of combined optimizers. The implementation for HalpernSGD can be accessed at: https://github.com/EttoreRitacco/HalpernSGD.git [ABSTRACT FROM AUTHOR]
ISSN:09259902
DOI:10.1007/s10844-025-00969-x