Mathematical foundations of neural network weight optimization
Journal of Information & Optimization Sciences · 2026 · 47 (5-B) · 2065-2073
DOI: 10.47974/jios-2297 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Information & Optimization Sciences, 2026. Verfasst von Madhuri B. Thorat und 4 weiteren Autor:innen.
Abstract (Originalsprache)
Neural network optimisation is a major problem in deep learning. It needs algorithms that work well with millions of parameters and keep convergence stable and generalisation. Stochastic gradient descent (SGD) and other traditional first-order methods are fast to compute, but they take a long time to converge and are sensitive to learning rate schedules. Second-order methods use curvature information to speed up optimisation, but they are too expensive for large networks. Adaptive methods like Adam and RMSProp are more stable and converge faster, but they don’t always work as well as SGD. In this paper presents a thorough mathematical examination of weight optimisation in neural networks, encompassing gradient-based methods, regularisation techniques, theoretical perspectives on loss landscapes, and comparative performance evaluations.
Zitieren
APA
Thorat, M. B., Wawage, V. P., Yadav, D. P., Pushpalatha, P., & Gandhi, Y. (2026). Mathematical foundations of neural network weight optimization. Journal of Information & Optimization Sciences, 47(5-B), 2065-2073. https://doi.org/10.47974/jios-2297
Vancouver
Thorat MB, Wawage VP, Yadav DP, Pushpalatha P, Gandhi Y. Mathematical foundations of neural network weight optimization. Journal of Information & Optimization Sciences. 2026;47(5-B):2065-2073. doi:10.47974/jios-2297
BibTeX
@article{Thorat2026,
author = {Thorat, Madhuri B. and Wawage, Vaishali Pawan and Yadav, Durga Prasad and Pushpalatha, P. and Gandhi, Yatin},
title = {Mathematical foundations of neural network weight optimization},
journal = {Journal of Information & Optimization Sciences},
year = {2026},
volume = {47},
number = {5-B},
pages = {2065--2073},
doi = {10.47974/jios-2297}
}
EUVIMED