Image de couverture de livre

DynMuon: A Dynamic Spectral Shaping View of Muon

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wu, Fangzhou, Shah, Rikhav, Silwal, Sandeep, Zhang, Qiuyi
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Randomization Boosts KV Caching, Learning Balances Query Load: A Joint Perspective
par: Wu, Fangzhou, et autres
Publié: (2026)

Capturing LLM Capabilities via Evidence-Calibrated Query Clustering
par: Wu, Fangzhou, et autres
Publié: (2026)

Efficient Training-Free Online Routing for High-Volume Multi-LLM Serving
par: Wu, Fangzhou, et autres
Publié: (2025)

Muon Dynamics as a Spectral Wasserstein Flow
par: Peyré, Gabriel
Publié: (2026)

Muon$^2$: Boosting Muon via Adaptive Second-Moment Preconditioning
par: Liu, Ziyue, et autres
Publié: (2026)

Preconditioning Benefits of Spectral Orthogonalization in Muon
par: Ma, Jianhao, et autres
Publié: (2026)

Intrinsic Muon: Spectral Optimization on Riemannian Matrix Manifolds
par: Li, Yibang, et autres
Publié: (2026)

HTMuon: Improving Muon via Heavy-Tailed Spectral Correction
par: Pang, Tianyu, et autres
Publié: (2026)

MiMuon: Mixed Muon Optimizer with Improved Generalization for Large Models
par: Huang, Feihu, et autres
Publié: (2026)

Muon is Scalable for LLM Training
par: Liu, Jingyuan, et autres
Publié: (2025)

The Newton-Muon Optimizer
par: Du, Zhehang, et autres
Publié: (2026)

Spectral Flattening Is All Muon Needs: How Orthogonalization Controls Learning Rate and Convergence
par: Nguyen, Tien-Phat, et autres
Publié: (2026)

Muon Optimizer Accelerates Grokking
par: Tveit, Amund, et autres
Publié: (2025)

FedMuon: Accelerating Federated Learning with Matrix Orthogonalization
par: Liu, Junkang, et autres
Publié: (2025)

DeMuon: A Decentralized Muon for Matrix Optimization over Graphs
par: He, Chuan, et autres
Publié: (2025)

Even Faster Kernel Matrix Linear Algebra via Density Estimation
par: Shah, Rikhav, et autres
Publié: (2025)

TrasMuon: Trust-Region Adaptive Scaling for Orthogonalized Momentum Optimizers
par: Cheng, Peng, et autres
Publié: (2026)

Delving into Muon and Beyond: Deep Analysis and Extensions
par: Qi, Xianbiao, et autres
Publié: (2026)

Mousse: Rectifying the Geometry of Muon with Curvature-Aware Preconditioning
par: Zhang, Yechen, et autres
Publié: (2026)

Optimizer-Induced Mode Connectivity: From AdamW to Muon
par: Zhang, Fangzhao, et autres
Publié: (2026)

Advancing Model Refinement: Muon-Optimized Distillation and Quantization for LLM Deployment
par: Sander, Jacob, et autres
Publié: (2026)

TEON: Tensorized Orthonormalization Beyond Layer-Wise Muon for Large Language Model Pre-Training
par: Zhang, Ruijie, et autres
Publié: (2026)

Muon Outperforms Adam in Tail-End Associative Memory Learning
par: Wang, Shuche, et autres
Publié: (2025)

Beyond Worst-Case Dimensionality Reduction for Sparse Vectors
par: Silwal, Sandeep, et autres
Publié: (2025)

Muon is Not That Special: Random or Inverted Spectra Work Just as Well
par: Shumaylov, Zakhar, et autres
Publié: (2026)

From Complex Dynamics to DynFormer: Rethinking Transformers for PDEs
par: Lai, Pengyu, et autres
Publié: (2026)

Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee
par: Zhu, Zehan, et autres
Publié: (2025)

Muon-OGD: Muon-based Spectral Orthogonal Gradient Projection for LLM Continual Learning
par: Lu, Binghang, et autres
Publié: (2026)

Prompts Generalize with Low Data: Non-vacuous Generalization Bounds for Optimizing Prompts with More Informative Priors
par: Madras, David, et autres
Publié: (2025)

AdaMuon: Adaptive Muon Optimizer
par: Si, Chongjie, et autres
Publié: (2025)

Shape-aware Graph Spectral Learning
par: Xu, Junjie, et autres
Publié: (2023)

Advancing Long-Term Multi-Energy Load Forecasting with Patchformer: A Patch and Transformer-Based Approach
par: Hong, Qiuyi, et autres
Publié: (2024)

Multi-View Spectral Clustering for Graphs with Multiple View Structures
par: Tsitsikas, Yorgos, et autres
Publié: (2025)

DynScaling: Efficient Verifier-free Inference Scaling via Dynamic and Integrated Sampling
par: Wang, Fei, et autres
Publié: (2025)

Ontology of Belief Diversity: A Community-Based Epistemological Approach
par: Fischella, Tyler, et autres
Publié: (2024)

An End-to-End Reinforcement Learning Based Approach for Micro-View Order-Dispatching in Ride-Hailing
par: Yue, Xinlang, et autres
Publié: (2024)

PRISM: Structured Optimization via Anisotropic Spectral Shaping
par: Yang, Yujie
Publié: (2026)

LSH-DynED: A Dynamic Ensemble Framework with LSH-Based Undersampling for Evolving Multi-Class Imbalanced Classification
par: Abadifard, Soheil, et autres
Publié: (2025)

Muon with Spectral Guidance: Efficient Optimization for Scientific Machine Learning
par: Lu, Binghang, et autres
Publié: (2026)

DynBERG: Dynamic BERT-based Graph neural network for financial fraud detection
par: Kulkarni, Omkar, et autres
Publié: (2025)