From Geometry to Generalization: Why Row Normalization Can Beat Adam and Muon
cs.LG, cs.AI, math.OC, stat.ML
Submitted: 2026-10-08
Updated: 2026-10-08
Terminology
Sources
- MuonEq: Balancing Before Orthogonalization with Lightweight Equilibration
- Aurora: A Leverage-Aware Spectral Optimizer
- AMUSE: Anytime Muon with Stable Gradient Evaluation
- To Each Optimizer a Norm, To Each Norm its Generalization
- On the Width Scaling of Neural Optimizers Under Matrix Operator Norms I: Row/Column Normalization and Hyperparameter Transfer
- Qwen3 Technical Report
- Nora: Normalized Orthogonal Row Alignment for Scalable Matrix Optimizer
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