כתבה
arXiv cs.AI ·
SGDM עם מומנטום: יציבות אלגוריתמית
Stochastic Gradient Descent with Momentum is Algorithmically Stable
SGDM עם מומנטום הוכח כיציב באלגוריתם. המחקר חוקר את יציבות SGDM ומסקנותיו יכולות לשפר את הביצועים של LLMs.
תקציר מקורי באנגליתarXiv:2605.28517v2 Announce Type: replace-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 training, it may degrade generalization. In this paper, we close this gap by developing a comprehensive generalization analysis of SGDM through the lens of algorithmic stability. More specifically, we introduce a generalized SGDM framework that encompasses both Polyak's and Nesterov's momentum schemes, and establish tight on-average model stability bounds for sm
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית