Process / pipeline
随机优化 — SGD 及其变体
随机优化是一类迭代方法，它通过在随机采样的数据子集（即小批量）上计算梯度来最小化目标函数，而不是一次性在整个数据集上计算。该方法由 Robbins 和 Monro 于 1951 年首次提出，当时称为随机逼近，后来通过 SGD with momentum、AdaGrad、RMSProp 和 Adam 等变体，成为训练大规模机器学习模型的标准引擎。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
来源
- Robbins, H. & Monro, S. (1951). A Stochastic Approximation Method. Annals of Mathematical Statistics, 22(3), 400-407. DOI: 10.1214/aoms/1177729586 ↗
- Kingma, D.P. & Ba, J. (2015). Adam: A Method for Stochastic Optimization. International Conference on Learning Representations (ICLR 2015). link ↗
如何引用本页
ScholarGate. (2026, June 1). Stochastic Optimization (SGD and Variants). ScholarGate. https://scholargate.app/zh/optimization/stochastic-optimization
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
Compare side by side →