当前位置: X-MOL 学术Optim. Methods Softw. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Optimized convergence of stochastic gradient descent by weighted averaging
Optimization Methods & Software ( IF 2.2 ) Pub Date : 2024-02-05 , DOI: 10.1080/10556788.2024.2306383
Melinda Hagedorn 1 , Florian Jarre 1
Affiliation  

Under mild assumptions stochastic gradient methods asymptotically achieve an optimal rate of convergence if the arithmetic mean of all iterates is returned as an approximate optimal solution. Howev...

中文翻译:

通过加权平均优化随机梯度下降的收敛性

在温和的假设下,如果所有迭代的算术平均值作为近似最优解返回,则随机梯度方法渐近地实现最佳收敛速度。然而...
更新日期:2024-02-05
down
wechat
bug