arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.09712stat.MLcs.LGmath.PR
收藏

神经网络的深度退化:初始化时全连接ReLU网络中的角度消失现象

Depth Degeneracy in Neural Networks: Vanishing Angles in Fully Connected ReLU Networks on Initialization

University of Guelph(圭尔夫大学)

Cameron Jakub, Mihai Nica

AI总结:

本文针对全连接ReLU网络初始化时的深度退化问题,通过组合展开推导输入夹角随深度趋零的精确公式,结合蒙特卡洛实验验证其对有限网络的近似效果,还发现了相关混合矩与Bessel数的组合关联。

摘要:

尽管深度神经网络在各类任务上表现出色,其诸多特性尚未得到理论层面的解释,深度退化现象就是其中之一:网络层数越深,初始化状态下的网络输出就越接近常值函数。本文研究了ReLU神经网络中两个输入之间的夹角随网络层数变化的演化规律,通过组合展开方法,推导得出该夹角随深度增加趋近于零的速率的精确公式。这些公式捕捉到了主流的无限宽极限框架无法观测到的微观波动,能够给出性质上存在差异的预测结果。本文通过蒙特卡洛实验验证了理论结果,证明所得结论可以精准近似有限宽度网络的行为,同时通过实证研究探究了深度退化现象对实际网络训练的负面影响。上述公式以经过ReLU函数的相关高斯变量的混合矩形式给出,本文还发现了这些混合矩与Bessel数之间出人意料的组合关联,可实现对这些矩的显式计算。

英文摘要:

Despite remarkable performance on a variety of tasks, many properties of deep neural networks are not yet theoretically understood. One such mystery is the depth degeneracy phenomenon: the deeper you make your network, the closer your network is to a constant function on initialization. In this paper, we examine the evolution of the angle between two inputs to a ReLU neural network as a function of the number of layers. By using combinatorial expansions, we find precise formulas for how fast this angle goes to zero as depth increases. These formulas capture microscopic fluctuations that are not visible in the popular framework of infinite width limits, and leads to qualitatively different predictions. We validate our theoretical results with Monte Carlo experiments and show that our results accurately approximate finite network behaviour. \review{We also empirically investigate how the depth degeneracy phenomenon can negatively impact training of real networks.} The formulas are given in terms of the mixed moments of correlated Gaussians passed through the ReLU function. We also find a surprising combinatorial connection between these mixed moments and the Bessel numbers that allows us to explicitly evaluate these moments.

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。

↑