The Road Taken: The Role of Optimizers at the Edge of Stability
cs.LG
Submitted: 2026-08-19
Updated: 2026-09-29
Sources
- Edge of Stochastic Stability: Revisiting the Edge of Stability for SGD
- The Map Behind the Flow: Finite-Step Gradient Descent as a Dynamical System
- Greedy Alignment Principle for Optimizer Selection
- Grokfast: Accelerated Grokking by Amplifying Slow Gradients
- The large learning rate phase of deep learning: the catapult mechanism
- The Origin of Edge of Stability
- Edge Flow: A Tractable and Predictive Continuous-Time Model for Gradient Descent at the Edge of Stability
- A Rod Flow Model for Adam at the Edge of Stability
- Rod Flow: A Continuous-Time Model for Gradient Descent at the Edge of Stability
- A Walk with SGD
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks