Anytime Training with Schedule-Free Spectral Optimization
cs.LG, cs.AI, math.OC, stat.ML
Submitted: 2026-05-21
Updated: 2026-09-25
Code: https://github.com/KellerJordan/Muon
Terminology
Sources
- LLaMA: Open and Efficient Foundation Language Models
- A Survey of Large Language Models
- Large Language Models: A Survey
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- A Survey on Vision-Language-Action Models for Embodied AI
- OpenVLA: An Open-Source Vision-Language-Action Model
- A Comprehensive Survey of Continual Learning: Theory, Method and Application
- Step-size Optimization for Continual Learning
- Anytime Pretraining: Horizon-Free Learning-Rate Schedules with Weight Averaging
- How far away are truly hyperparameter-free learning algorithms?
- Training Compute-Optimal Large Language Models
- MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
- Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations
- Model Merging in Pre-training of Large Language Models
- Averaging Weights Leads to Wider Optima and Better Generalization
- Adam: A Method for Stochastic Optimization
- AdaMuon: Adaptive Muon Optimizer
- NorMuon: Making Muon more efficient and scalable
- Dion: Distributed Orthonormalized Updates
- Dion2: A Simple Method to Shrink Matrix in Muon
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