Full-batch gradient descent forces the largest Hessian eigenvalue to exactly 2/η via the edge coupling functional, its criticality condition, and the mean value theorem with no gap.
Arnol'd , title =
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
-
The Origin of Edge of Stability
Full-batch gradient descent forces the largest Hessian eigenvalue to exactly 2/η via the edge coupling functional, its criticality condition, and the mean value theorem with no gap.