arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1904.01367stat.MLcs.LG
收藏

为什么ResNet有效?恢复性概括

Why ResNet Works? Residuals Generalize

University of Sydney(悉尼大学)

Fengxiang He, Tongliang Liu, Dacheng Tao

摘要:

剩余连接显著提高了深度神经网络的性能。然而,很少有理论结果解决残差对深度神经网络的假设复杂性和泛化能力的影响。本文从假设空间的覆盖数角度研究了剩余连接对神经网络假设复杂度的影响。证明了当权矩阵和非线性项的总数固定时,覆盖数的上界与链式神经网络相同,无论它们是否在残差中.这一结果表明,与链状网络相比,剩余连接可能不会增加神经网络的假设复杂性。基于覆盖数的上界,我们然后获得ResNet的基于$\mathcal O(1 / \sqrt{N})$边缘的多类泛化界,作为具有剩余连接的任何深度神经网络的示例情况。对于类似的最先进的神经网络架构(如DenseNet和ResNeXt)的泛化保证是直接的。从我们的泛化界中总结出一种实际的实现方法:为了获得良好的泛化能力,我们需要使用正则化项来控制权矩阵的范数的大小不增加太多,这证明了标准的权衰减技术是正确的。

英文摘要:

Residual connections significantly boost the performance of deep neural networks. However, there are few theoretical results that address the influence of residuals on the hypothesis complexity and the generalization ability of deep neural networks. This paper studies the influence of residual connections on the hypothesis complexity of the neural network in terms of the covering number of its hypothesis space. We prove that the upper bound of the covering number is the same as chain-like neural networks, if the total numbers of the weight matrices and nonlinearities are fixed, no matter whether they are in the residuals or not. This result demonstrates that residual connections may not increase the hypothesis complexity of the neural network compared with the chain-like counterpart. Based on the upper bound of the covering number, we then obtain an $\mathcal O(1 / \sqrt{N})$ margin-based multi-class generalization bound for ResNet, as an exemplary case of any deep neural network with residual connections. Generalization guarantees for similar state-of-the-art neural network architectures, such as DenseNet and ResNeXt, are straight-forward. From our generalization bound, a practical implementation is summarized: to approach a good generalization ability, we need to use regularization terms to control the magnitude of the norms of weight matrices not to increase too much, which justifies the standard technique of weight decay.

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。

↑