Adversarial Training with Large Step Sizes: Implicit Bias, Optimization, and Sharpness
cs.LG, math.OC
Submitted: 2026-11-05
Updated: 2026-11-05
Terminology
Sources
- A Modern Look at the Relationship between Sharpness and Generalization
- Convergence and Margin of Adversarial Training on Separable Data
- Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability
- Sharpness-Aware Minimization for Efficiently Improving Generalization
- Adversarial Training for Gradient Descent: Analysis Through its Continuous-time Approximation
- Non-Euclidean Gradient Descent Operates at the Edge of Stability
- Risk and parameter convergence of logistic regression
- Gradient Descent on Logistic Regression with Non-Separable Data and Large Step Sizes
- Zeroth-Order Optimization at the Edge of Stability
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis