A long-standing obstacle to progress in deep learning is the problem of vanishing and exploding gradients. The problem has largely been overcome through the introduction of carefully constructed initializations and batch normalization. Nevertheless, architectures incorporating skip-connections such as resnets perform much better than standard feedforward architectures despite well-chosen initialization and batch normalization. In this paper, we identify the shattered gradients problem. Specifically, we show that the correlation between gradients in standard feedforward networks decays exponentially with depth resulting in gradients that resemble white noise. In contrast, the gradients in architectures with skip-connections are far more resistant to shattering decaying sublinearly. Detailed empirical evidence is presented in support of the analysis, on both fully-connected networks and convnets. Finally, we present a new "looks linear" (LL) initialization that prevents shattering. Preliminary experiments show the new initialization allows to train very deep networks without the addition of skip-connections.

本文提出了“破碎梯度”问题，指出标准前馈网络中梯度之间的相关性随着深度呈指数衰减，导致梯度类似于白噪声；相比之下，具有跳跃连接的体系结构更加抗干扰，梯度呈次线性降低。此外，本文还提出了一种新的“线性外观”(LL)初始化方法，可以避免破碎现象，并证明其可以使深度网络更好地进行训练。

破碎渐变问题：如果 ResNets 是答案，那问题是什么？