Enhanced NIRMAL Optimizer With Damped Nesterov Acceleration: A Comparative Analysis

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Gaud, Nirmal, Murthy, Prasad Krishna, Hassan, Mostaque Md. Morshedur, Ganguly, Abhijit, Mali, Vinay, Randive, Ms Lalita Bhagwat, Singh, Abhaypratap
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915457425997824
author Gaud, Nirmal
Murthy, Prasad Krishna
Hassan, Mostaque Md. Morshedur
Ganguly, Abhijit
Mali, Vinay
Randive, Ms Lalita Bhagwat
Singh, Abhaypratap
author_facet Gaud, Nirmal
Murthy, Prasad Krishna
Hassan, Mostaque Md. Morshedur
Ganguly, Abhijit
Mali, Vinay
Randive, Ms Lalita Bhagwat
Singh, Abhaypratap
contents This study introduces the Enhanced NIRMAL (Novel Integrated Robust Multi-Adaptation Learning with Damped Nesterov Acceleration) optimizer, an improved version of the original NIRMAL optimizer. By incorporating an $(α, r)$-damped Nesterov acceleration mechanism, Enhanced NIRMAL improves convergence stability while retaining chess-inspired strategies of gradient descent, momentum, stochastic perturbations, adaptive learning rates, and non-linear transformations. We evaluate Enhanced NIRMAL against Adam, SGD with Momentum, Nesterov, and the original NIRMAL on four benchmark image classification datasets: MNIST, FashionMNIST, CIFAR-10, and CIFAR-100, using tailored convolutional neural network (CNN) architectures. Enhanced NIRMAL achieves a test accuracy of 46.06\% and the lowest test loss (1.960435) on CIFAR-100, surpassing the original NIRMAL (44.34\% accuracy) and closely rivaling SGD with Momentum (46.43\% accuracy). These results underscore Enhanced NIRMAL's superior generalization and stability, particularly on complex datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16550
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhanced NIRMAL Optimizer With Damped Nesterov Acceleration: A Comparative Analysis
Gaud, Nirmal
Murthy, Prasad Krishna
Hassan, Mostaque Md. Morshedur
Ganguly, Abhijit
Mali, Vinay
Randive, Ms Lalita Bhagwat
Singh, Abhaypratap
Information Retrieval
Artificial Intelligence
This study introduces the Enhanced NIRMAL (Novel Integrated Robust Multi-Adaptation Learning with Damped Nesterov Acceleration) optimizer, an improved version of the original NIRMAL optimizer. By incorporating an $(α, r)$-damped Nesterov acceleration mechanism, Enhanced NIRMAL improves convergence stability while retaining chess-inspired strategies of gradient descent, momentum, stochastic perturbations, adaptive learning rates, and non-linear transformations. We evaluate Enhanced NIRMAL against Adam, SGD with Momentum, Nesterov, and the original NIRMAL on four benchmark image classification datasets: MNIST, FashionMNIST, CIFAR-10, and CIFAR-100, using tailored convolutional neural network (CNN) architectures. Enhanced NIRMAL achieves a test accuracy of 46.06\% and the lowest test loss (1.960435) on CIFAR-100, surpassing the original NIRMAL (44.34\% accuracy) and closely rivaling SGD with Momentum (46.43\% accuracy). These results underscore Enhanced NIRMAL's superior generalization and stability, particularly on complex datasets.
title Enhanced NIRMAL Optimizer With Damped Nesterov Acceleration: A Comparative Analysis
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2508.16550