arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2011.02150cs.LGstat.ML
收藏

EAdam优化器:$ε$如何影响Adam

EAdam Optimizer: How $ε$ Impact Adam

Tianjin University(天津大学)

Wei Yuan, Kai-Xin Gao

摘要:

在深度学习中已经提出并使用了许多自适应优化方法,其中Adam被视为默认算法,广泛应用于许多深度学习框架中。近年来,人们提出了Adabaround、RDam和Adabelief等Adam的变体,它们的性能都优于Adam。然而,这些变种主要集中在改变步长的梯度或平方it.Motivated的事实,适当的阻尼是重要的成功的强大的二阶优化,我们讨论了亚当在本文中的常数$ε$的影响。令人惊讶的是,我们可以获得更好的性能比亚当简单地改变$ε$的位置。基于这一发现,我们提出了一种新的亚当变体,称为EAdam,它不需要额外的超参数或计算成本。我们还讨论了我们的方法和亚当之间的联系和区别。最后,我们对各种流行的任务和模型进行了广泛的实验。实验结果表明,与Adam方法相比,该方法能带来显著的改进.我们的代码可在https://github.com/yuanwei2019/EAdam-optimizer上获得。

英文摘要:

Many adaptive optimization methods have been proposed and used in deep learning, in which Adam is regarded as the default algorithm and widely used in many deep learning frameworks. Recently, many variants of Adam, such as Adabound, RAdam and Adabelief, have been proposed and show better performance than Adam. However, these variants mainly focus on changing the stepsize by making differences on the gradient or the square of it. Motivated by the fact that suitable damping is important for the success of powerful second-order optimizers, we discuss the impact of the constant $ε$ for Adam in this paper. Surprisingly, we can obtain better performance than Adam simply changing the position of $ε$. Based on this finding, we propose a new variant of Adam called EAdam, which doesn't need extra hyper-parameters or computational costs. We also discuss the relationships and differences between our method and Adam. Finally, we conduct extensive experiments on various popular tasks and models. Experimental results show that our method can bring significant improvement compared with Adam. Our code is available at https://github.com/yuanwei2019/EAdam-optimizer.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑