Optimization lies at the heart of machine learning (ML) and signal processing (SP). Contemporary approaches based on the stochastic gradient (SG) method are nonadaptive in the sense that their implementation employs prescribed parameter values that need to be tuned for each application. This article summarizes recent research and motivates future work on adaptive stochastic optimization methods, which have the potential to offer significant computational savings when training largescale systems.

中文翻译：

---

自适应随机优化：分析随机优化算法的框架

优化是机器学习 (ML) 和信号处理 (SP) 的核心。基于随机梯度 (SG) 方法的现代方法是非自适应的，因为它们的实现采用了需要针对每个应用进行调整的规定参数值。本文总结了最近的研究，并激发了未来关于自适应随机优化方法的工作，这些方法有可能在训练大规模系统时提供显着的计算节省。