{"total":35,"rows":[{"id":"2603.28254","title":"MuonEq: Balancing Before Orthogonalization with Lightweight Equilibration","created":"2026-03-30","cited_by_count":17,"area":null},{"id":"2603.20527","title":"RMNP: Row-Momentum Normalized Preconditioning for Scalable Matrix-Based Optimization","created":"2026-03-20","cited_by_count":15,"area":null},{"id":"2603.26554","title":"Sharp Capacity Scaling of Spectral Optimizers in Learning Associative Memory","created":"2026-03-27","cited_by_count":14,"area":null},{"id":"2602.11948","title":"Insights on Muon from Simple Quadratics","created":"2026-02-12","cited_by_count":13,"area":null},{"id":"2605.09238","title":"Intrinsic Muon: Spectral Optimization on Riemannian Matrix Manifolds","created":"2026-05-10","cited_by_count":6,"area":null},{"id":"2606.04662","title":"Why Muon Outperforms Adam: A Curvature Perspective","created":"2026-06-03","cited_by_count":6,"area":null},{"id":"2608.26288","title":"Muon with Finite Newton-Schulz: The Smoothing Benefit in Nonsmooth Nonconvex Optimization","created":"2026-08-26","cited_by_count":5,"area":null},{"id":"2606.27715","title":"Aurora: A Leverage-Aware Spectral Optimizer","created":"2026-06-26","cited_by_count":4,"area":null},{"id":"2605.19619","title":"MiMuon: Mixed Muon Optimizer with Improved Generalization for Large Models","created":"2026-05-19","cited_by_count":3,"area":null},{"id":"2606.16371","title":"CacheMuon: Using Temporal Preconditioning To Approximate Polar Factor","created":"2026-06-15","cited_by_count":3,"area":null},{"id":"2605.09176","title":"Navigating LLM Valley: From AdamW to Memory-Efficient and Matrix-Based Optimizers","created":"2026-05-09","cited_by_count":2,"area":null},{"id":"2605.12994","title":"DP-Muon: Differentially Private Optimization via Matrix-Orthogonalized Momentum","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2605.18528","title":"Tight Complexity of Muon under Heavy-Tailed Noise","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2605.21803","title":"Same Architecture, Different Capacity: Optimizer-Induced Spectral Scaling Laws","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2606.21514","title":"Towards Understanding the Power and Limits of the Muon Optimizer: A River-Valley Perspective","created":"2026-06-19","cited_by_count":2,"area":null},{"id":"2606.27216","title":"Hierarchical Muon: Tiled Newton-Schulz Updates for Efficient Muon Optimization","created":"2026-06-25","cited_by_count":2,"area":null},{"id":"2609.30546","title":"Convergence guarantees for Muon: New parameter regimes and generalizations","created":"2026-09-24","cited_by_count":2,"area":null},{"id":"2605.24770","title":"Muon in Vision Transformers: Optimizer-Recipe Interactions and Gradient Spectra","created":"2026-05-23","cited_by_count":1,"area":null},{"id":"2606.01720","title":"A Note on Stability for Orthogonalized Matrix Momentum with Client Sampling","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2606.08783","title":"OptMuon: Closed-Loop Orthogonalized Momentum Methods for Stochastic Optimization with Zero-Noise Optimality","created":"2026-06-07","cited_by_count":1,"area":null},{"id":"2607.13246","title":"Reassessing Muon for Matrix Factorization","created":"2026-07-14","cited_by_count":1,"area":null},{"id":"2607.14536","title":"Muse: Representation Geometry of Muon Beyond Normalized Momentum","created":"2026-07-16","cited_by_count":1,"area":null},{"id":"2609.39595","title":"Convergence of Practical Muon with Finite Newton-Schulz Iterations and Nesterov Momentum","created":"2026-09-30","cited_by_count":1,"area":null},{"id":"2603.09923","title":"OptEMA: Adaptive Exponential Moving Average for Stochastic Optimization with Zero-Noise Optimality","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2605.05577","title":"Accelerating LMO-Based Optimization via Implicit Gradient Transport","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.14970","title":"Zero-order Parameter-free Optimization for LMO-based Methods: Novel Approach for Efficient Fine-tuning","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2608.12710","title":"Federated Compositional Muon Optimizer for Matrix-Wise Models","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2609.13677","title":"Nonsmooth Optimization via Orthogonalized Momentum","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.32861","title":"Muon Under Gradient Noise and the Limits of Orthogonalization Near Optima","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33047","title":"Cost-free Spectral Estimation for Adaptive Newton--Schulz in Matrix Optimizers","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.33152","title":"Convergence of Practical Muon","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.39114","title":"The Row Normalization Puzzle in Muon","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02738","title":"Inner Momentum for Differentially Private Muon","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.03306","title":"Training-Loss Guarantees for Muon with Finite-Step Newton--Schulz Orthogonalization","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.20112","title":"From Spectral to Frobenius: When Muon Loses Its Spectral Implicit Bias","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}