{"total":67,"rows":[{"id":"2510.05491","title":"NorMuon: Making Muon more efficient and scalable","created":"2025-10-07","cited_by_count":84,"area":null},{"id":"2509.26030","title":"Muon Outperforms Adam in Tail-End Associative Memory Learning","created":"2025-09-30","cited_by_count":46,"area":null},{"id":"2509.15816","title":"On the Convergence of Muon and Beyond","created":"2025-09-19","cited_by_count":31,"area":null},{"id":"2509.02981","title":"AdaGrad Meets Muon: Adaptive Stepsizes for Orthogonal Updates","created":"2025-09-03","cited_by_count":23,"area":null},{"id":"2512.20399","title":"GeoTransolver: Learning Physics on Irregular Domains Using Multi-scale Geometry Aware Physics Attention Transformer","created":"2025-12-23","cited_by_count":23,"area":null},{"id":"2512.05620","title":"Hyperparameter Transfer Enables Consistent Gains of Matrix-Preconditioned Optimizers Across Scales","created":"2025-12-05","cited_by_count":21,"area":null},{"id":"2509.11983","title":"Low-rank Orthogonalization for Large-scale Matrix Optimization with Applications to Foundation Model Training","created":"2025-09-15","cited_by_count":18,"area":null},{"id":"2603.09697","title":"Mousse: Rectifying the Geometry of Muon with Curvature-Aware Preconditioning","created":"2026-03-10","cited_by_count":17,"area":null},{"id":"2603.28254","title":"MuonEq: Balancing Before Orthogonalization with Lightweight Equilibration","created":"2026-03-30","cited_by_count":17,"area":null},{"id":"2604.09967","title":"Muon$^2$: Boosting Muon via Adaptive Second-Moment Preconditioning","created":"2026-04-11","cited_by_count":17,"area":null},{"id":"2510.25000","title":"What Really Matters in Matrix-Whitening Optimizers?","created":"2025-10-28","cited_by_count":16,"area":null},{"id":"2511.20626","title":"ROOT: Robust Orthogonalized Optimizer for Neural Network Training","created":"2025-11-25","cited_by_count":15,"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":"2602.17080","title":"Adam Improves Muon: Adaptive Moment Estimation with Orthogonalized Momentum","created":"2026-02-19","cited_by_count":14,"area":null},{"id":"2605.11181","title":"Muon is Not That Special: Random or Inverted Spectra Work Just as Well","created":"2026-05-11","cited_by_count":14,"area":null},{"id":"2603.10067","title":"HTMuon: Improving Muon via Heavy-Tailed Spectral Correction","created":"2026-03-10","cited_by_count":12,"area":null},{"id":"2605.18106","title":"Symmetry-Compatible Principle for Optimizer Design: Embeddings, LM Heads, SwiGLU MLPs, and MoE Routers","created":"2026-05-18","cited_by_count":11,"area":"moe"},{"id":"2603.14315","title":"Enhancing LLM Training via Spectral Clipping","created":"2026-03-15","cited_by_count":10,"area":null},{"id":"2605.19282","title":"Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR","created":"2026-05-19","cited_by_count":8,"area":"lr"},{"id":"2511.06086","title":"MuonAll: Muon Variant for Efficient Finetuning of Large Language Models","created":"2025-11-08","cited_by_count":7,"area":null},{"id":"2602.12429","title":"Stabilizing Native Low-Rank LLM Pretraining","created":"2026-02-12","cited_by_count":6,"area":null},{"id":"2602.21545","title":"MUON+: Towards More Effective Muon via One Additional Normalization Step for LLM Pre-training","created":"2026-02-25","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":"2607.20548","title":"SOAP, Muon, and Beyond: Pushing LLM Pretraining Scales","created":"2026-07-13","cited_by_count":6,"area":null},{"id":"2511.20584","title":"A Tale of Two Geometries: Adaptive Optimizers and Non-Euclidean Descent","created":"2025-11-25","cited_by_count":5,"area":null},{"id":"2605.13079","title":"Spectral Flattening Is All Muon Needs: How Orthogonalization Controls Learning Rate and Convergence","created":"2026-05-13","cited_by_count":5,"area":null},{"id":"2510.01377","title":"DeMuon: A Decentralized Muon for Matrix Optimization over Graphs","created":"2025-10-01","cited_by_count":4,"area":null},{"id":"2512.09678","title":"Ky Fan Norms and Beyond: Dual Norms and Combinations for Matrix Optimization","created":"2025-12-10","cited_by_count":4,"area":null},{"id":"2602.06880","title":"Decoupling Variance and Scale-Invariant Updates in Adaptive Gradient Descent for Unified Vector and Matrix Optimization","created":"2026-02-06","cited_by_count":4,"area":null},{"id":"2603.15914","title":"The Agentic Researcher: A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning","created":"2026-03-16","cited_by_count":4,"area":"agents"},{"id":"2603.17970","title":"Beyond Muon: MUD (MomentUm Decorrelation) for Faster Transformer Training","created":"2026-03-18","cited_by_count":4,"area":null},{"id":"2510.14009","title":"Noise-Adaptive Layerwise Learning Rates: Accelerating Geometry-Aware Optimization for Deep Neural Network Training","created":"2025-10-15","cited_by_count":3,"area":null},{"id":"2602.01105","title":"OLion: Approaching the Hadamard Ideal by Intersecting Spectral and $\\ell_{\\infty}$ Implicit Biases","created":"2026-02-01","cited_by_count":3,"area":null},{"id":"2604.12968","title":"Evolution of Optimization Methods: Algorithms, Scenarios, and Evaluations","created":"2026-04-14","cited_by_count":3,"area":null},{"id":"2605.23061","title":"Anytime Training with Schedule-Free Spectral Optimization","created":"2026-05-21","cited_by_count":3,"area":null},{"id":"2606.09658","title":"Muon Learns More Robust and Transferable Features than Adam","created":"2026-06-08","cited_by_count":3,"area":null},{"id":"2509.18396","title":"Development of Deep Learning Optimizers: Approaches, Concepts, and Update Rules","created":"2025-09-22","cited_by_count":2,"area":null},{"id":"2604.17423","title":"A unified convergence theory for adaptive first-order methods in the nonconvex case, including AdaNorm, full and diagonal AdaGrad and Muon","created":"2026-04-19","cited_by_count":2,"area":null},{"id":"2605.06615","title":"When and Why SignSGD Outperforms SGD: A Theoretical Study Based on $\\ell_1$-norm Lower Bounds","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2605.07067","title":"PolarAdamW: Disentangling Spectral Control and Schur Gauge-Equivariance in Matrix Optimisation","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2605.26977","title":"Convergence of Spectral Descent for Non-smooth Optimization","created":"2026-05-26","cited_by_count":2,"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":"2606.06418","title":"Double Preconditioning (DoPr): Optimization for Test-Time Performance, not Validation Loss","created":"2026-06-04","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":"2606.13867","title":"Muon$^p$: Muon with Fractional Spectral Powers","created":"2026-06-11","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":"2608.05088","title":"MALT: Lightweight Curvature-Aware Muon via Diagonal Preconditioning","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2608.25990","title":"Spectral Allocation: Why Muon Outperforms Adam, and How to Improve Muon","created":"2026-08-26","cited_by_count":1,"area":null},{"id":"2601.14603","title":"Variance-Adaptive Muon: Pre-Orthogonalization Variance Modulation for Efficient Language Model Pretraining","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2605.19781","title":"From SGD to Muon: Adaptive Optimization via Schatten-p Norms","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.26842","title":"MONA: Muon Optimizer with Nesterov Acceleration for Scalable Language Model Training","created":"2026-05-26","cited_by_count":0,"area":"moe"},{"id":"2605.27733","title":"Can Entry-Wise Clipping Give Spectral Control of Stochastic Gradients?","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.01787","title":"Stochastic convergence of parallel asynchronous adaptive first-order methods","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.10406","title":"FOGO: Forgetting-aware Orthogonalization Optimizer","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.14187","title":"Zeta: Dual Whitening for Matrix Optimization via Coordinate-Adaptive Preconditioning","created":"2026-06-12","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":"2606.30634","title":"One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.04033","title":"OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2608.28557","title":"Blog: Survey of Optimizers","created":"2026-08-28","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":"2609.36692","title":"Normalize-Then-Precondition: A Hierarchical Approach to Marginal Scale and Interaction Geometry for LLM Training","created":"2026-09-29","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":"2610.01395","title":"AF-Muon: An AdamW-Free Muon Optimizer for Tied-Embedding Models","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.02705","title":"MuonIO: Principled Norm-Aware Descent for Embedding Tables and Language Model Heads","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.09040","title":"ORACLE: Optimizer-Relative Alignment for Constrained LEarning","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.10975","title":"Optimizing Large Language Models with Chained LMOs","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.17285","title":"Which Geometry on Which Layer? Measured Sign-Spectral Assignment in Mixed-Optimizer Training","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}