AI RESEARCH
Momentum Further Constrains Sharpness at the Edge of Stochastic Stability
arXiv CS.LG
•
ArXi:2604.14108v1 Announce Type: new Recent work suggests that (stochastic) gradient descent self-organizes near an instability boundary, shaping both optimization and the solutions found. Momentum and mini-batch gradients are widely used in practical deep learning optimization, but it remains unclear whether they operate in a comparable regime of instability. We nstrate that SGD with momentum exhibits an Edge of Stochastic Stability (EoSS)-like regime with batch-size-dependent behavior that cannot be explained by a single momentum-adjusted stability threshold.