Benign Overfitting of Two-Layer ReLU Networks in Fixed Dimension through Localized Initialization
cs.LG, cs.AI, stat.ML
Submitted: 2025-05-16
Updated: 2026-11-15
Terminology
Sources
- Characterizing Overfitting in Kernel Ridgeless Regression Through the Eigenspectrum
- Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension
- Provable Tempered Overfitting of Minimal Nets and Typical Nets
- From Tempered to Benign Overfitting in ReLU Neural Networks
- Benign Overfitting for Two-layer ReLU Convolutional Neural Networks
- Generalization Ability of Wide Neural Networks on $\mathbb{R}$
- Towards an Understanding of Benign Overfitting in Neural Networks
- Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality
- Regularised Least-Squares Regression with Infinite-Dimensional Output Space
- Improved Convergence Guarantees for Shallow Neural Networks
- Rethinking Benign Overfitting in Two-Layer Neural Networks
- Feature Learning in Infinite-Width Neural Networks
- Sobolev norm inconsistency of kernel interpolation
- A Unifying View on Implicit Bias in Training Linear Neural Networks
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