{"ID":2885713,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.04293","arxiv_id":"2508.04293","title":"Comparative Analysis of Novel NIRMAL Optimizer Against Adam and SGD with Momentum","abstract":"This study proposes NIRMAL (Novel Integrated Robust Multi-Adaptation Learning), a novel optimization algorithm that combines multiple strategies inspired by the movements of the chess piece. These strategies include gradient descent, momentum, stochastic perturbations, adaptive learning rates, and non-linear transformations. We carefully evaluated NIRMAL against two widely used and successful optimizers, Adam and SGD with Momentum, on four benchmark image classification datasets: MNIST, FashionMNIST, CIFAR-10, and CIFAR-100. The custom convolutional neural network (CNN) architecture is applied on each dataset. The experimental results show that NIRMAL achieves competitive performance, particularly on the more challenging CIFAR-100 dataset, where it achieved a test accuracy of 45.32\\%and a weighted F1-score of 0.4328. This performance surpasses Adam (41.79\\% accuracy, 0.3964 F1-score) and closely matches SGD with Momentum (46.97\\% accuracy, 0.4531 F1-score). Also, NIRMAL exhibits robust convergence and strong generalization capabilities, especially on complex datasets, as evidenced by stable training results in loss and accuracy curves. These findings underscore NIRMAL's significant ability as a versatile and effective optimizer for various deep learning tasks.","short_abstract":"This study proposes NIRMAL (Novel Integrated Robust Multi-Adaptation Learning), a novel optimization algorithm that combines multiple strategies inspired by the movements of the chess piece. These strategies include gradient descent, momentum, stochastic perturbations, adaptive learning rates, and non-linear transforma...","url_abs":"https://arxiv.org/abs/2508.04293","url_pdf":"https://arxiv.org/pdf/2508.04293v1","authors":"[\"Nirmal Gaud\",\"Surej Mouli\",\"Preeti Katiyar\",\"Vaduguru Venkata Ramya\"]","published":"2025-08-06T10:30:22Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.AI\"]","methods":"[\"Convolutional Neural Network\"]","has_code":false}