改进的优化器在复杂图像数据上表现更稳，准确率接近最先进方法。
Enhanced NIRMAL Optimizer With Damped Nesterov Acceleration: A Comparative Analysis
- 引入阻尼版Nesterov加速机制，提升收敛稳定性。
- 在CIFAR-100上达到46.06%准确率，低于原版但逼近SGD+动量。
- 适合追求稳定训练的深度学习模型优化场景。
本研究提出增强版NIRMAL（Novel Integrated Robust Multi-Adaptation Learning with Damped Nesterov Acceleration）优化器，通过引入$(α, r)$-阻尼Nesterov加速机制，在保持原版棋类启发式策略的基础上，提升了收敛稳定性。该方法在四个基准图像分类数据集（MNIST、FashionMNIST、CIFAR-10、CIFAR-100）上与Adam、SGD+动量、Nesterov及原始NIRMAL进行对比，采用定制化的卷积神经网络架构。在CIFAR-100上，增强版NIRMAL取得46.06%的测试准确率和最低的测试损失（1.960435），优于原始NIRMAL（44.34%准确率），并接近SGD+动量（46.43%准确率）。结果表明，该优化器在复杂数据集上具有更优的泛化能力与稳定性。
原文摘要 · Abstract (English)
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.
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。