Under specific conditions, gradient descent converges in the unstable edge-of-stability regime for a quadratic loss on a depth-2 diagonal linear network, with a bias bound depending on step size and initialization.
Understanding gradient descent on the edge of stability in deep learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Criteria and Bias of Parameterized Linear Regression under Edge of Stability Regime
Under specific conditions, gradient descent converges in the unstable edge-of-stability regime for a quadratic loss on a depth-2 diagonal linear network, with a bias bound depending on step size and initialization.