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 1906.09235cs.LGmath.OCstat.ML
收藏

通用深度神经网络的频率原理理论

Theory of the Frequency Principle for General Deep Neural Networks

Department of Mathematics, Purdue University(普渡大学数学系);New York University Abu Dhabi and Courant Institute(纽约大学阿布扎比分校及柯朗研究所)

Tao Luo, Zheng Ma, Zhi-Qin John Xu, Yaoyu Zhang

AI总结:

本文严格研究了通用深度神经网络在训练过程中从低频到高频学习目标函数的频率原理,并给出了三个阶段的定理。

摘要:

随着深度神经网络(DNN)在现实问题中的广泛应用,最近一些关于DNN的实证研究报告了一个普遍现象——频率原理(F-Principle):在训练过程中,DNN倾向于从低频到高频学习目标函数。频率原理在提供对DNN的定性和定量理解方面非常有用。在本文中,我们严格研究了通用DNN在训练动态的三个阶段:初始阶段、中间阶段和最终阶段的频率原理。对于每个阶段,我们根据表征频率原理的适当量提供了一个定理。我们的结果是通用的,因为它们适用于具有一般激活函数、数据种群密度和一大类损失函数的多层网络。我们的工作为更好地理解DNN训练过程的频率原理奠定了理论基础。

英文摘要:

Along with fruitful applications of Deep Neural Networks (DNNs) to realistic problems, recently, some empirical studies of DNNs reported a universal phenomenon of Frequency Principle (F-Principle): a DNN tends to learn a target function from low to high frequencies during the training. The F-Principle has been very useful in providing both qualitative and quantitative understandings of DNNs. In this paper, we rigorously investigate the F-Principle for the training dynamics of a general DNN at three stages: initial stage, intermediate stage, and final stage. For each stage, a theorem is provided in terms of proper quantities characterizing the F-Principle. Our results are general in the sense that they work for multilayer networks with general activation functions, population densities of data, and a large class of loss functions. Our work lays a theoretical foundation of the F-Principle for a better understanding of the training process of DNNs.

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。

↑