AdamZ: An Enhanced Optimisation Method for Neural Network Training

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zaznov, Ilia, Badii, Atta, Dufour, Alfonso, Kunkel, Julian
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917847387602944
author Zaznov, Ilia
Badii, Atta
Dufour, Alfonso
Kunkel, Julian
author_facet Zaznov, Ilia
Badii, Atta
Dufour, Alfonso
Kunkel, Julian
contents AdamZ is an advanced variant of the Adam optimiser, developed to enhance convergence efficiency in neural network training. This optimiser dynamically adjusts the learning rate by incorporating mechanisms to address overshooting and stagnation, that are common challenges in optimisation. Specifically, AdamZ reduces the learning rate when overshooting is detected and increases it during periods of stagnation, utilising hyperparameters such as overshoot and stagnation factors, thresholds, and patience levels to guide these adjustments. While AdamZ may lead to slightly longer training times compared to some other optimisers, it consistently excels in minimising the loss function, making it particularly advantageous for applications where precision is critical. Benchmarking results demonstrate the effectiveness of AdamZ in maintaining optimal learning rates, leading to improved model performance across diverse tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2411_15375
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AdamZ: An Enhanced Optimisation Method for Neural Network Training
Zaznov, Ilia
Badii, Atta
Dufour, Alfonso
Kunkel, Julian
Machine Learning
Artificial Intelligence
Neural and Evolutionary Computing
Optimization and Control
AdamZ is an advanced variant of the Adam optimiser, developed to enhance convergence efficiency in neural network training. This optimiser dynamically adjusts the learning rate by incorporating mechanisms to address overshooting and stagnation, that are common challenges in optimisation. Specifically, AdamZ reduces the learning rate when overshooting is detected and increases it during periods of stagnation, utilising hyperparameters such as overshoot and stagnation factors, thresholds, and patience levels to guide these adjustments. While AdamZ may lead to slightly longer training times compared to some other optimisers, it consistently excels in minimising the loss function, making it particularly advantageous for applications where precision is critical. Benchmarking results demonstrate the effectiveness of AdamZ in maintaining optimal learning rates, leading to improved model performance across diverse tasks.
title AdamZ: An Enhanced Optimisation Method for Neural Network Training
topic Machine Learning
Artificial Intelligence
Neural and Evolutionary Computing
Optimization and Control
url https://arxiv.org/abs/2411.15375