新优化器LyAm结合稳定性理论，提升噪声环境下的训练鲁棒性。
LyAm: Robust Non-Convex Optimization for Stable Learning in Noisy Environments
- 用李雅普诺夫理论动态调学习率，增强收敛稳定性。
- 在CIFAR-10和CIFAR-100上精度更高、收敛更快更稳定。
- 适合对训练稳定性要求高的视觉任务场景。
深度神经网络训练，尤其在计算机视觉任务中，常受噪声梯度和不稳收敛影响，制约性能与泛化能力。本文提出新型优化器LyAm，融合Adam的自适应动量估计与基于李雅普诺夫的稳定性机制。LyAm利用李雅普诺夫稳定性理论动态调整学习率，提升复杂非凸环境下收敛的鲁棒性，并提供严格的理论框架证明其在非凸设置下的收敛保证。在CIFAR-10和CIFAR-100上的大量实验表明，LyAm在精度、收敛速度和稳定性方面均持续优于现有最优优化器，是鲁棒深度学习优化的有力候选方案。
原文摘要 · Abstract (English)
Training deep neural networks, particularly in computer vision tasks, often suffers from noisy gradients and unstable convergence, which hinder performance and generalization. In this paper, we propose LyAm, a novel optimizer that integrates Adam's adaptive moment estimation with Lyapunov-based stability mechanisms. LyAm dynamically adjusts the learning rate using Lyapunov stability theory to enhance convergence robustness and mitigate training noise. We provide a rigorous theoretical framework proving the convergence guarantees of LyAm in complex, non-convex settings. Extensive experiments on like as CIFAR-10 and CIFAR-100 show that LyAm consistently outperforms state-of-the-art optimizers in terms of accuracy, convergence speed, and stability, establishing it as a strong candidate for robust deep learning optimization.
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。