On Lipschitz Explosion in Deep Neural Networks with Normalization: Consequences for Optimization and Adversarial Robustness
cs.LG, cs.AI, math.OC, stat.ML
Submitted: 2026-11-05
Updated: 2026-11-05
Terminology
Sources
- Layer Normalization
- On the Complexity of Finding Small Subgradients in Nonsmooth Optimization
- Batch Normalization is a Cause of Adversarial Vulnerability
- A Mean Field Theory of Batch Normalization
- On the Gap Between Strict-Saddles and True Convexity: An Omega(log d) Lower Bound for Eigenvector Approximation
- On the Complexity of Deterministic Nonsmooth and Nonconvex Optimization
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