SGD stabilizes sharpness below 2/η with equilibrium gap ΔS = η β σ_u²/(4α) due to noise-enhanced stochastic self-stabilization.
How SGD selects the global minima in over-parameterized learning: A dynamical stability perspective
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SGD at the Edge of Stability: The Stochastic Sharpness Gap
SGD stabilizes sharpness below 2/η with equilibrium gap ΔS = η β σ_u²/(4α) due to noise-enhanced stochastic self-stabilization.