Stochastic Gradient Descent with Momentum is Algorithmically Stable 事件

Stochastic Gradient Descent with Momentum is Algorithmically Stable arXiv:2605.28517v1 Announce Type: cross Abstract: Stochastic gradient descent with momentum (SGDM) is one of the most widely used optimization algorithms in machine learning. While optimization properties of SGDM have been extensively studied in the literature, it remains insufficiently understood whether and when SGDM can generalize well to unseen data. In particular, it has been conjectured that while momentum accelerates tra