AF-Muon: An AdamW-Free Muon Optimizer for Tied-Embedding Models
cs.LG
Submitted: 2026-10-01
Updated: 2026-10-01
Code: https://github.com/arashlagzian/afmoun
Sources
- Old Optimizer, New Norm: An Anthology
- On the Convergence of Muon and Beyond
- Muse: Representation Geometry of Muon Beyond Normalized Momentum
- Optimal Scaling Needs Optimal Norm
- Memory-Efficient LLM Pretraining via Minimalist Optimizer Design
- DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing
- Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling
- Adam: A Method for Stochastic Optimization
- Symmetry-Compatible Principle for Optimizer Design: Embeddings, LM Heads, SwiGLU MLPs, and MoE Routers
- NorMuon: Making Muon more efficient and scalable
- DeepSeek-V3 Technical Report
- Muon is Scalable for LLM Training
- Decoupled Weight Decay Regularization
- MuonAll: Muon Variant for Efficient Finetuning of Large Language Models
- Optimistic Dual Averaging Unifies Modern Optimizers
- Convergence Analysis of Muon-type Methods with Inexact LMO in the Degenerate Case
- Gluon: Making Muon & Scion Great Again! (Bridging Theory and Practice of LMO-based Optimizers for LLMs)
- AdaMuon: Adaptive Muon Optimizer
- Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
- Chameleon: Mixed-Modal Early-Fusion Foundation Models
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks