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

arXiv:2610.01459 · cs.LG, stat.ML · Submitted 2026-10-01 · Read on arXiv

cs.LG, stat.ML

Submitted: 2026-10-01

Updated: 2026-10-01

Terminology

• Edge of Stability — 12× in this paper
• Ambient Dimension — 4× in this paper · explained in 1 episode
• Regularization — 2× in this paper · explained in 3 episodes
• Adaptive Gradient Methods — 1× in this paper · explained in 1 episode
• Generalization — 1× in this paper · explained in 13 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Spectral Gap — 1× in this paper · explained in 5 episodes

Sources

• Edge of Stochastic Stability: Revisiting the Edge of Stability for SGD
• Adaptive Gradient Methods at the Edge of Stability
• Understanding Optimization in Deep Learning with Central Flows
• The large learning rate phase of deep learning: the catapult mechanism
• Gradient Descent on Logistic Regression: Do Large Step-Sizes Work with Data on the Sphere?
• A Defense of the Quadratic Model

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks