Cloud & Infra
impact 16
SGD at the Edge of Stability: The Stochastic Sharpness Gap
SGD at the Edge of Stability: The Stochastic Sharpness Gap arXiv:2604.21016v1 Announce Type: cross Abstract: When training neural networks with full-batch gradient descent (GD) and step size $\eta$, the largest eigenval…
Why it matters
The timing matters: edge is converging with shifts in stability, which could amplify the downstream impact.