Geometry of learning dynamics: Gradient descent versus natural gradient on the ridge of optimization
cs.LG, cs.NE
Submitted: 2026-09-15
Updated: 2026-09-16
Comments: 11 pages, 5 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Empirical Analysis of the Hessian of Over-Parametrized Neural Networks
- Information Geometric Self-Organization at the Edge of Stability in High-Capacity Kernel Associative Memories
- Dual Riemannian Newton Method on Statistical Manifolds
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