https://marovi.ai/index.php?action=history&feed=atom&title=Translations%3AStochastic_Gradient_Descent%2F25%2Fzh 2026-04-27T22:02:11Z Revision history for this page on the wiki MediaWiki 1.39.1 https://marovi.ai/index.php?title=Translations:Stochastic_Gradient_Descent/25/zh&diff=5470&oldid=prev 2026-04-27T03:38:16Z

<p>Batch translate Stochastic Gradient Descent unit 25 → zh</p> <p><b>New page</b></p><div>{| class=&quot;wikitable&quot;<br /> |-<br /> ! 方法 !! 核心思想 !! 文献<br /> |-<br /> | &#039;&#039;&#039;{{Term|momentum|Momentum}}&#039;&#039;&#039; || 对历史梯度累积指数衰减的移动平均 || Polyak, 1964<br /> |-<br /> | &#039;&#039;&#039;Nesterov 加速梯度&#039;&#039;&#039; || 在“前瞻”位置上计算梯度 || Nesterov, 1983<br /> |-<br /> | &#039;&#039;&#039;Adagrad&#039;&#039;&#039; || 为每个参数设置学习率，对频繁更新的特征逐步减小 || Duchi et al., 2011<br /> |-<br /> | &#039;&#039;&#039;RMSProp&#039;&#039;&#039; || 利用平方梯度的移动平均修正 Adagrad 学习率不断衰减的问题 || Hinton（讲义），2012<br /> |-<br /> | &#039;&#039;&#039;{{Term|Adam}}&#039;&#039;&#039; || 将 {{Term|momentum}} 与 RMSProp 风格的自适应学习率结合 || Kingma 与 Ba, 2015<br /> |-<br /> | &#039;&#039;&#039;AdamW&#039;&#039;&#039; || 将权重衰减与自适应梯度更新解耦 || Loshchilov 与 Hutter, 2019<br /> |}</div>

DeployBot