Cohen et al. (2021) empirically study the evolution of the largest eigenvalue of the loss Hessian, also known as sharpness, along the gradient descent (GD) trajectory and observe a phenomenon called the Edge of Stability (EoS). The sharpness increases at the early phase of training (referred to as progressive sharpening), and eventually saturates close to the threshold of $2 / \text{(step size)}$. In this paper, we start by demonstrating through empirical studies that when the EoS phenomenon occurs, different GD trajectories (after a proper reparameterization) align on a specific bifurcation diagram independent of initialization. We then rigorously prove this trajectory alignment phenomenon for a two-layer fully-connected linear network and a single-neuron nonlinear network trained with a single data point. Our trajectory alignment analysis establishes both progressive sharpening and EoS phenomena, encompassing and extending recent findings in the literature.

通过实证研究，证明最大特征值（也被称为锐度）沿着梯度下降轨迹的演化呈现出一种叫做稳定边缘现象（EoS）的现象，进一步证明了在合适的重新参数化下，不同的梯度下降轨迹会在一个特定的分叉图上对齐，从而建立了锐度逐步增加和EoS现象的理论分析。

轨迹对齐：通过分岔理论理解稳定边缘现象