arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.00294cs.LGcs.NEmath.STstat.MEstat.MLstat.TH
收藏

正则化神经网络的统计保证

Statistical Guarantees for Regularized Neural Networks

Ruhr-University Bochum(波鸿鲁尔大学)

Mahsa Taheri, Fang Xie, Johannes Lederer

摘要:

神经网络已经成为数据分析的标准工具,但它们缺乏全面的数学理论。例如,从数据中学习神经网络的统计保证非常少,特别是对于在实践中使用或至少类似于此类的估计器的类别。在本文中,我们开发了一个一般的统计保证估计,包括一个最小二乘项和正则化。然后,我们用$\ell_1$ -正则化来证明这一保证,表明相应的预测误差在层的数量上最多以次线性方式增加,在参数的总数上最多以几何方式增加。我们的研究结果为神经网络的正则化估计建立了数学基础,它们加深了我们对神经网络和深度学习的数学理解。

英文摘要:

Neural networks have become standard tools in the analysis of data, but they lack comprehensive mathematical theories. For example, there are very few statistical guarantees for learning neural networks from data, especially for classes of estimators that are used in practice or at least similar to such. In this paper, we develop a general statistical guarantee for estimators that consist of a least-squares term and a regularizer. We then exemplify this guarantee with $\ell_1$-regularization, showing that the corresponding prediction error increases at most sub-linearly in the number of layers and at most logarithmically in the total number of parameters. Our results establish a mathematical basis for regularized estimation of neural networks, and they deepen our mathematical understanding of neural networks and deep learning more generally.

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。

↑