新优化器NIRMAL在复杂图像数据上表现优于Adam，接近SGD-Momentum。
Comparative Analysis of Novel NIRMAL Optimizer Against Adam and SGD with Momentum
- 融合棋子运动机制的多策略优化算法
- 在CIFAR-100上达45.32%准确率，超Adam近4个百分点
- 适合追求稳定收敛与泛化能力的深度学习任务
本研究提出新型优化算法NIRMAL（Novel Integrated Robust Multi-Adaptation Learning），结合梯度下降、动量、随机扰动、自适应学习率和非线性变换等策略，受棋子运动启发。在MNIST、FashionMNIST、CIFAR-10和CIFAR-100四个图像分类基准数据集上，使用定制卷积神经网络（CNN）进行评估。结果表明，NIRMAL在更复杂的CIFAR-100上表现优异，测试准确率达45.32%，加权F1分数为0.4328，优于Adam（41.79%准确率，0.3964 F1分数），并接近SGD with Momentum（46.97%准确率，0.4531 F1分数）。同时，其训练损失与精度曲线稳定，展现出强鲁棒性与泛化能力，证明其在多种深度学习任务中的有效性与通用性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。