arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.01384cs.LGmath.OCstat.ML
收藏

过参数化深度ReLU网络梯度下降算法的泛化误差界

Generalization Error Bounds of Gradient Descent for Learning Over-parameterized Deep ReLU Networks

University of California, Los Angeles(加利福尼亚大学洛杉矶分校)

Yuan Cao, Quanquan Gu

摘要:

实证研究表明,基于梯度的方法可以学习深度神经网络(DNN),在过参数化机制中具有非常好的泛化性能,其中DNN可以很容易地适应训练数据的随机标记。最近,一系列工作在理论上解释了,通过过度参数化和适当的随机初始化,基于梯度的方法可以找到DNN训练损失的全局最小值。然而,现有的泛化误差界无法解释过参数DNN的良好泛化性能。现有的推广界的主要局限性是它们是基于一致收敛的,并且与训练算法无关。在这项工作中,我们推导出深度ReLU网络的算法相关泛化误差界,并表明在对数据分布的某些假设下,具有适当随机初始化的梯度下降(GD)能够训练一个充分过参数化的DNN,以实现任意小的泛化误差。我们的工作有助于解释过参数化深度神经网络的良好泛化性能。

英文摘要:

Empirical studies show that gradient-based methods can learn deep neural networks (DNNs) with very good generalization performance in the over-parameterization regime, where DNNs can easily fit a random labeling of the training data. Very recently, a line of work explains in theory that with over-parameterization and proper random initialization, gradient-based methods can find the global minima of the training loss for DNNs. However, existing generalization error bounds are unable to explain the good generalization performance of over-parameterized DNNs. The major limitation of most existing generalization bounds is that they are based on uniform convergence and are independent of the training algorithm. In this work, we derive an algorithm-dependent generalization error bound for deep ReLU networks, and show that under certain assumptions on the data distribution, gradient descent (GD) with proper random initialization is able to train a sufficiently over-parameterized DNN to achieve arbitrarily small generalization error. Our work sheds light on explaining the good generalization performance of over-parameterized deep neural networks.

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。

↑