Convergence Analysis of Newton's Method for Neural Networks in the Overparameterized Limit
cs.LG, math.PR, stat.ML
Submitted: 2026-05-08
Updated: 2026-09-26
Terminology
Sources
- Regularized Gauss-Newton for Optimizing Overparameterized Neural Networks
- Scalable Second Order Optimization for Deep Learning
- Gram-Gauss-Newton Method: Learning Overparameterized Neural Networks for Regression Problems
- A Riemannian Optimization Perspective of the Gauss-Newton Method for Feedforward Neural Networks
- AdaFisher: Adaptive Second Order Optimization via Fisher Information
- Curvature-Aware Optimization for High-Accuracy Physics-Informed Neural Networks
- Scaling Limit of Neural Networks with the Xavier Initialization and Convergence to a Global Minimum
- Discovery of Unstable Singularities
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