arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.00873cs.LGstat.ML
收藏

基于局部Rademacher复杂度的深度神经网络正则化实证研究

An Empirical Study on Regularization of Deep Neural Networks by Local Rademacher Complexity

Baidu Research(百度研究院);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

Yingzhen Yang, Jiahui Yu, Xingjian Li, Jun Huan, Thomas S. Huang

摘要:

为了提高深度神经网络(DNN)的泛化能力,对DNN进行正则化是一项重要而具有挑战性的工作。这方面的发展有利于DNN的理论基础,并促进其在人工智能的不同领域的可用性。在本文中,我们研究了Rademacher复杂性在提高DNN泛化能力方面的作用,并提出了一种新的正则化器,它植根于局部Rademacher复杂性(LRC)。虽然Rademacher复杂度是众所周知的函数类的无分布复杂度度量,有助于提高统计学习方法的泛化能力,但广泛的研究表明,LRC,其对应的限制函数类,在有限的训练样本下,收敛速度更快,泛化能力更强。我们的基于LRC的正则化器是通过估计以DNN的经验损失的最小值为中心的函数类的复杂度来开发的。在不同类型的网络结构上的实验证明了LRC正则化在提高泛化能力方面的有效性。此外,我们的方法具有最先进的结果CIFAR- $10$数据集与神经结构搜索发现的网络结构。

英文摘要:

Regularization of Deep Neural Networks (DNNs) for the sake of improving their generalization capability is important and challenging. The development in this line benefits theoretical foundation of DNNs and promotes their usability in different areas of artificial intelligence. In this paper, we investigate the role of Rademacher complexity in improving generalization of DNNs and propose a novel regularizer rooted in Local Rademacher Complexity (LRC). While Rademacher complexity is well known as a distribution-free complexity measure of function class that help boost generalization of statistical learning methods, extensive study shows that LRC, its counterpart focusing on a restricted function class, leads to sharper convergence rates and potential better generalization given finite training sample. Our LRC based regularizer is developed by estimating the complexity of the function class centered at the minimizer of the empirical loss of DNNs. Experiments on various types of network architecture demonstrate the effectiveness of LRC regularization in improving generalization. Moreover, our method features the state-of-the-art result on the CIFAR-$10$ dataset with network architecture found by neural architecture search.

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。

↑