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 2005.11879stat.MLcs.LGmath.PRmath.STstat.TH
收藏

线性宽度神经网络的共轭核和神经切核的谱

Spectra of the Conjugate Kernel and Neural Tangent Kernel for linear-width neural networks

Yale University(耶鲁大学);University of California, San Diego(加利福尼亚大学圣地亚哥分校);Department of Statistics and Data Science(统计与数据科学系);Department of Mathematics(数学系)

Zhou Fan, Zhichao Wang

摘要:

研究了多层前向神经网络的共轭核和神经切核的特征值分布。在一个渐近制度,网络宽度线性增加的样本量,随机初始化的权重,并为输入样本满足近似成对正交的概念,我们表明,CK和NTK的特征值分布收敛到确定性的限制。CK的限制是通过在隐藏层上迭代Marcenko-Pastur映射来描述的。NTK的极限等价于CK矩阵跨层的线性组合的极限,并且可以通过扩展该Marcenko-Pastur映射的递归定点方程来描述。我们证明了这些渐近预测与合成和CIFAR-10训练数据的观测光谱的一致性,并且我们进行了一个小的模拟来研究这些光谱在训练过程中的演变。

英文摘要:

We study the eigenvalue distributions of the Conjugate Kernel and Neural Tangent Kernel associated to multi-layer feedforward neural networks. In an asymptotic regime where network width is increasing linearly in sample size, under random initialization of the weights, and for input samples satisfying a notion of approximate pairwise orthogonality, we show that the eigenvalue distributions of the CK and NTK converge to deterministic limits. The limit for the CK is described by iterating the Marcenko-Pastur map across the hidden layers. The limit for the NTK is equivalent to that of a linear combination of the CK matrices across layers, and may be described by recursive fixed-point equations that extend this Marcenko-Pastur map. We demonstrate the agreement of these asymptotic predictions with the observed spectra for both synthetic and CIFAR-10 training data, and we perform a small simulation to investigate the evolutions of these spectra over training.

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。

↑