method · first seen 5 Oct 2026
Muon optimizer
Also: Muon, spectral optimizer, orthogonalized momentum, MomentUm Orthogonalized by Newton-Schulz
A matrix-aware optimizer that orthogonalizes weight updates using a polar decomposition approximation.
Mentions per week
PapersCodeDiscussion
Rank 83 on 16 Nov 2026 · 39 mentions in 28 days · 35 independent groups · papers → code · first seen 6 weeks ago · acceleration -0.69
Earliest sources
- ORCA: The Annealed Spectral Conditioning Optimizer for Faster, Better LLM TrainingPapers · 5 Oct 2026 · Yuanshi Liu, Boyuan Jiang, Liang Hou, Xin Tao, Pengfei Wan, Zhouchen Lin, Cong F…
- On the Comparison of Optimizers for Imbalanced LearningPapers · 5 Oct 2026 · Cl{é}ment Lezane, Fran{\c c}ois Bachoc, J{é}r{ô}me Bolte, Jean-Michel Loubes
- Muon Is Theoretically Wrong For Convolutions, But Empirically EffectivePapers · 5 Oct 2026 · Thibaut Boissin, Thomas Massena, Mathieu Serrurier, Franck Mamalet
- DGA-Muon: Decoupled Geometry-Aligned Adaptive Scaling for MuonPapers · 5 Oct 2026 · Wenpeng Zhang, Runsheng Yu
- Does Muon Need Fine-Grained Spectral Shaping?Papers · 5 Oct 2026 · Meher Chaitanya, Tianyi Zhou, Aristides Gionis
- Spectrally Targeted MuonPapers · 7 Oct 2026 · Vishrut Goyal, Rohan Ramkumar
Latest sources
- U-HamGNN: a universal model for magnetic Hamiltonians conditioned on spin and Hubbard UPapers · 15 Nov 2026 · Hongyu Yu, Yinze Hu, Yizhou Chen, Yang Cheng, Yingwei Chen, Xingao Gong, Yang Zh…
- High-dimensional limit theorems for adaptive variants of SGD I: Ballistic limitsPapers · 14 Nov 2026 · Aukosh Jagannath, Varnan Sarangian
- Muon Attains $\mathcal{O}(\varepsilon^{-3})$ Iteration Complexity under ShufflingPapers · 13 Nov 2026 · Kun Huang, Shi Pu, Karl Henrik Johansson
- Delayed Effects of Temporary Weight Decay in Muon PretrainingPapers · 13 Nov 2026 · Md Rifat Arefin, Ravid Shwartz-Ziv, Ernie Chang, Chinnadhurai Sankar, Rylan Conw…
- Factored One-sided Adam-Moment for Practical and Scalable SOAPPapers · 12 Nov 2026 · Jaemyung Yu, Byeongho Heo, Sangdoo Yun, Dongyoon Han
- SS-HSDP: Efficient and Flexible Sharded Data Parallelism via Runtime-Update DecouplingPapers · 12 Nov 2026 · Chendong Xiang, Pengle Zhang, Jinliang Li, Zichen Liang, Jintao Zhang, Fan Bao,…
- Byzantine-Robust Muon: Resilient Momentum Orthogonalization for Distributed LearningPapers · 9 Nov 2026 · Grigory Malinovsky, Yury Demidovich, Peter Richtárik
- DisMUSE: An Efficient Distributed Singular-Spectrum-Based Optimization Approach with Theoretical Convergence GuaranteePapers · 6 Nov 2026 · Zhen Qin, Zhiyao Zhang, Yingbin Liang, Jia Liu
- BiMuon: A Geometry-Aware Stochastic Bilevel Optimization ApproachPapers · 6 Nov 2026 · Zhen Qin, Zhiyao Zhang, Yingbin Liang, Jia Liu
- Module-Aware Optimization for Graph Neural NetworksPapers · 5 Nov 2026 · Guy Hadad, Haggai Roitman, Moshe Eliasof, Bracha Shapira
- DMuon-2: Scaling Matrix Optimizers in Data Parallelism with Topology-Aware Matrix Ownership and CommunicationPapers · 4 Nov 2026 · Starrick Liu, Ruizhi Chengze, Lufang Chen, Michael Zhao, Ran Yu, Xiaofan Li, Dan…
- Finite Spectral Depth Controls Gaussian Entrance Rank and Avoidance of the First Gradient-Flow SaddlePapers · 3 Nov 2026 · Yanlin Long