Product-Stability: Provable Convergence for Gradient Descent on the Edge of Stability
cs.LG
Submitted: 2026-04-03
Updated: 2026-09-26
Terminology
Sources
- Learning threshold neurons via the "edge of stability"
- Understanding Gradient Descent on Edge of Stability in Deep Learning
- Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization
- Sharp Minima Can Generalize For Deep Nets
- (S)GD over Diagonal Linear Networks: Implicit Regularisation, Large Stepsizes and Edge of Stability
- Fantastic Generalization Measures and Where to Find Them
- On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima
- Gradient Descent with Large Step Sizes: Chaos and Fractal Convergence Region
- Beyond the Quadratic Approximation: the Multiscale Structure of Neural Network Loss Landscapes
- Good regularity creates large learning rate implicit biases: edge of stability, balancing, and catapult
- Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability
- Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency
- Minimax Optimal Convergence of Gradient Descent in Logistic Regression via Large and Adaptive Stepsizes
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