新优化器Ano分离方向与步长，更抗噪声，适合强化学习等复杂场景。
ANO : Faster is Better in Noisy Landscape
- 方向用动量平滑，步长由瞬时梯度大小决定，解耦设计提升稳定性
- 在强化学习等高噪声任务中性能显著优于Adam、Adan，低噪声任务仍保持竞争力
- 提出Anolog改进参数敏感性，对动量系数不敏感，更适合实际应用
随机优化器是深度学习的核心，但如Adam和Adan等常用方法在非平稳或噪声环境中性能下降，部分原因在于其依赖动量的幅度估计。本文提出Ano，一种新型优化器，将方向与幅度解耦：动量仅用于方向平滑，而步长由瞬时梯度幅度决定。该设计增强了对梯度噪声的鲁棒性，同时保持一阶方法的简洁与高效。进一步提出Anolog，通过对数调度扩展动量窗口，消除对动量系数的敏感性。理论证明了非凸收敛性，收敛速率与其它符号基方法相当。实验表明，Ano在强化学习等高噪声、非平稳场景中表现显著提升，而在低噪声任务上仍具竞争力。
原文摘要 · Abstract (English)
Stochastic optimizers are central to deep learning, yet widely used methods such as Adam and Adan can degrade in non-stationary or noisy environments, partly due to their reliance on momentum-based magnitude estimates. We introduce Ano, a novel optimizer that decouples direction and magnitude: momentum is used for directional smoothing, while instantaneous gradient magnitudes determine step size. This design improves robustness to gradient noise while retaining the simplicity and efficiency of first-order methods. We further propose Anolog, which removes sensitivity to the momentum coefficient by expanding its window over time via a logarithmic schedule. We establish non-convex convergence guarantees with a convergence rate similar to other sign-based methods, and empirically show that Ano provides substantial gains in noisy and non-stationary regimes such as reinforcement learning, while remaining competitive on low-noise 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。