提出自适应梯度方法OSGM-Best，性能媲美拟牛顿法且更省内存。
Gradient Methods with Online Scaling Part II. Practical Aspects
- 基于在线凸优化设计自适应步长，实现动态调整
- OSGM-Best在测试中达到拟牛顿法水平，迭代开销更低
- 适用于非凸优化，可对接现有优化理论体系
本文聚焦于在线缩放梯度方法（OSGM）的实践层面。我们利用OSGM框架设计新的自适应一阶优化方法，并揭示其经验行为特征。所提出的OSGM-Best方法在性能上与拟牛顿变体相当，但所需内存更少、每次迭代代价更低。此外，我们将OSGM扩展至非凸优化问题，并梳理了其与现有优化理论与实践分支的潜在联系。
原文摘要 · Abstract (English)
Part I of this work [Gao25] establishes online scaled gradient methods (OSGM), a framework that utilizes online convex optimization to adapt stepsizes in gradient methods. This paper focuses on the practical aspects of OSGM. We leverage the OSGM framework to design new adaptive first-order methods and provide insights into their empirical behavior. The resulting method, OSGM-Best, matches the performance of quasi-Newton variants while requiring less memory and cheaper iterations. We also extend OSGM to nonconvex optimization and outline directions that connect OSGM to existing branches of optimization theory and practice.
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。