Tight Transition Time Bounds for Separable Logistic Regression at the Edge of Stability

Excerpt

arXiv:2610.01459v1 Announce Type: new Abstract: We study logistic regression on linearly separable data under gradient descent with a large constant stepsize $\eta$. Such dynamics may exhibit a characteristic Edge of Stability phenomenon, in which the loss initially oscillates before transitioning to a stable phase of monotone decrease. Existing work provides a tight $\Theta(1)$ bound in dimension $d=2$ as $\eta \to \infty$ and conjectures a bound independent of $\eta$ in arbitrary dimensions $d