Variance-Adaptive Muon: Pre-Orthogonalization Variance Modulation for Efficient Language Model Pretraining
cs.LG
Submitted: 2026-01-21
Updated: 2026-09-01
Code: https://github.com/jingru-lee/Variance-Adaptive-Muon
Terminology
Sources
- Muon Optimizes Under Spectral Norm Constraints
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Training Compute-Optimal Large Language Models
- Scaling Laws for Neural Language Models
- Adam: A Method for Stochastic Optimization
- Noise Is Not the Main Factor Behind the Gap Between SGD and Adam on Transformers, but Sign Descent Might Be
- NorMuon: Making Muon more efficient and scalable
- Cautious Optimizers: Improving Training with One Line of Code
- Muon is Scalable for LLM Training
- Decoupled Weight Decay Regularization
- In Search of Adam's Secret Sauce
- DeepOBS: A Deep Learning Optimizer Benchmark Suite
- Benchmarking Optimizers for Large Language Model Pretraining
- SOAP: Improving and Stabilizing Shampoo using Adam
- The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training
- Fantastic Pretraining Optimizers and Where to Find Them
- Qwen3 Technical Report
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