Gradient descent at the Edge of Stability: free energy model and kinetic description of the two-layer network 文章

ArXiv CS.AI2026-06-06NEWSen作者: Antonin Chodron de Courcel
查看原文 →
关系图谱

Gradient descent at the Edge of Stability: free energy model and kinetic description of the two-layer network · 相关技术

相关技术

Edge of StabilityGradient Descent