{"total":68,"rows":[{"id":"2409.20325","title":"Old Optimizer, New Norm: An Anthology","created":"2024-09-30","cited_by_count":193,"area":null},{"id":"2502.07529","title":"Training Deep Learning Models with Norm-Constrained LMOs","created":"2025-02-11","cited_by_count":192,"area":null},{"id":"2505.02222","title":"Practical Efficiency of Muon for Pretraining","created":"2025-05-04","cited_by_count":80,"area":null},{"id":"2505.01618","title":"Don't be lazy: CompleteP enables compute-efficient deep transformers","created":"2025-05-02","cited_by_count":78,"area":null},{"id":"2410.21265","title":"Modular Duality in Deep Learning","created":"2024-10-28","cited_by_count":77,"area":null},{"id":"2505.13416","title":"Gluon: Making Muon & Scion Great Again! (Bridging Theory and Practice of LMO-based Optimizers for LLMs)","created":"2025-05-19","cited_by_count":72,"area":null},{"id":"2410.01131","title":"nGPT: Normalized Transformer with Representation Learning on the Hypersphere","created":"2024-10-01","cited_by_count":70,"area":null},{"id":"2504.05295","title":"Dion: Distributed Orthonormalized Updates","created":"2025-04-07","cited_by_count":68,"area":null},{"id":"2503.20762","title":"ASGO: Adaptive Structured Gradient Optimization","created":"2025-03-26","cited_by_count":57,"area":null},{"id":"2407.17465","title":"u-$\\mu$P: The Unit-Scaled Maximal Update Parametrization","created":"2024-07-24","cited_by_count":29,"area":null},{"id":"2510.09827","title":"An Exploration of Non-Euclidean Gradient Descent: Muon and its Many Variants","created":"2025-10-10","cited_by_count":28,"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":"2507.13338","title":"Training Transformers with Enforced Lipschitz Constants","created":"2025-07-17","cited_by_count":20,"area":null},{"id":"2510.22980","title":"How Muon's Spectral Design Benefits Generalization: A Study on Imbalanced Data","created":"2025-10-27","cited_by_count":19,"area":null},{"id":"2410.22069","title":"Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks","created":"2024-10-29","cited_by_count":18,"area":null},{"id":"2506.07254","title":"A Stable Whitening Optimizer for Efficient Neural Network Training","created":"2025-06-08","cited_by_count":18,"area":null},{"id":"2506.01913","title":"Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness","created":"2025-06-02","cited_by_count":17,"area":null},{"id":"2510.27403","title":"FedMuon: Accelerating Federated Learning with Matrix Orthogonalization","created":"2025-10-31","cited_by_count":16,"area":null},{"id":"2512.16928","title":"Dion2: A Simple Method to Shrink Matrix in Muon","created":"2025-12-01","cited_by_count":13,"area":null},{"id":"2601.20205","title":"Hyperparameter Transfer with Mixture-of-Expert Layers","created":"2026-01-28","cited_by_count":13,"area":"moe"},{"id":"2601.23000","title":"Mano: Restriking Manifold Optimization for LLM Training","created":"2026-01-30","cited_by_count":12,"area":null},{"id":"2603.09952","title":"On the Width Scaling of Neural Optimizers Under Matrix Operator Norms I: Row/Column Normalization and Hyperparameter Transfer","created":"2026-03-10","cited_by_count":12,"area":null},{"id":"2410.05838","title":"Time Transfer: On Optimal Learning Rate and Batch Size In The Infinite Data Limit","created":"2024-10-08","cited_by_count":9,"area":null},{"id":"2501.12243","title":"FOCUS: First Order Concentrated Updating Scheme","created":"2025-01-21","cited_by_count":8,"area":null},{"id":"2501.12391","title":"Physics of Skill Learning","created":"2025-01-21","cited_by_count":8,"area":null},{"id":"2510.03871","title":"Optimal Scaling Needs Optimal Norm","created":"2025-10-04","cited_by_count":8,"area":null},{"id":"2602.09314","title":"Clarifying Shampoo: Adapting Spectral Descent to Stochasticity and the Parameter Trajectory","created":"2026-02-10","cited_by_count":8,"area":null},{"id":"2603.21191","title":"On the Role of Batch Size in Stochastic Conditional Gradient Methods","created":"2026-03-22","cited_by_count":7,"area":null},{"id":"2509.23500","title":"Beyond Outliers: A Study of Optimizers Under Quantization","created":"2025-09-27","cited_by_count":6,"area":null},{"id":"2602.13498","title":"TrasMuon: Trust-Region Adaptive Scaling for Orthogonalized Momentum Optimizers","created":"2026-02-13","cited_by_count":6,"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":"2605.10797","title":"Muown: Row-Norm Control for Muon Optimization","created":"2026-05-11","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":"2512.17131","title":"Smoothing DiLoCo with Primal Averaging for Faster Training of LLMs","created":"2025-12-18","cited_by_count":5,"area":null},{"id":"2502.17405","title":"Function-Space Learning Rates","created":"2025-02-24","cited_by_count":4,"area":null},{"id":"2507.08091","title":"Low-rank Momentum Factorization for Memory Efficient Training","created":"2025-07-10","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":"2603.02064","title":"Never Saddle for Reparameterized Steepest Descent as Mirror Flow","created":"2026-03-02","cited_by_count":4,"area":null},{"id":"2606.12921","title":"LoRA-Muon: Spectral Steepest Descent on the Low-Rank Manifold","created":"2026-06-11","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":"2604.27077","title":"Learning Rate Transfer in Normalized Transformers","created":"2026-04-29","cited_by_count":3,"area":null},{"id":"2605.19458","title":"Implicit Bias of Mirror Flow in Homogeneous Neural Networks: Sparse and Dense Feature Learning","created":"2026-05-19","cited_by_count":3,"area":null},{"id":"2602.01212","title":"SimpleGPT: Improving GPT via A Simple Normalization Strategy","created":"2026-02-01","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":"2606.15268","title":"When to use what Schatten-$p$ norm in deep learning?","created":"2026-06-13","cited_by_count":2,"area":null},{"id":"2512.04632","title":"Turbo-Muon: Almost-Orthogonal Pre-Conditioning for Fast Muon Updates","created":"2025-12-04","cited_by_count":1,"area":null},{"id":"2605.06316","title":"Pro-KLShampoo: Projected KL-Shampoo with Whitening Recovered by Orthogonalization","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.11316","title":"Error whitening: Why Gauss-Newton outperforms Newton","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2605.18999","title":"Distance-Aware Muon: Adaptive Step Scaling for Normalized Optimization","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2606.15702","title":"Schattor: Schatten-family methods for deep learning optimization","created":"2026-06-14","cited_by_count":1,"area":null},{"id":"2608.09763","title":"Second-Order Muon Done Right: A Principled Marriage of Spectral Geometry and Curvature","created":"2026-08-10","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":"2504.16381","title":"Follow the MEP: Scalable Neural Representations for Minimum-Energy Path Discovery in Molecular Systems","created":"2025-04-23","cited_by_count":0,"area":null},{"id":"2603.03610","title":"Riemannian Optimization in Modular Systems","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2605.21104","title":"HORST: Composing Optimizer Geometries for Sparse Transformer Training","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2607.04535","title":"ManifoldFlow: Spectrum-Learnable Stiefel Optimization via SPD Relaxation","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2607.29674","title":"Sign compression for Muon: SignMuon, MuonSign, and the Limits of Error Feedback","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.04026","title":"A Trust-region Framework for Moment Estimation","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2608.22253","title":"Toward a First-Principles Update Geometry for the Language-Model Head","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.08381","title":"Equivariance Breaks the Learning Rate","created":"2026-09-08","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":"2609.25745","title":"Modular Norm RandOpt: Population-Efficient Ensembling through Architecture-Aware Perturbations","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.26811","title":"The Drift Contract: Spectral Updates for Depth-Robust Local Learning","created":"2026-09-16","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":"2610.13773","title":"Geometry-Aware Multi-Objective Optimization: Norm-Constrained Oracles with Entropic Weight Updates","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.14344","title":"On the Depth Transfer of Neural Optimizers via L-Smoothness","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.17588","title":"Taming Softmax at the Limits of Muon: A Unified Approach through Hilbert Geometry","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19552","title":"Test-Time Forecasting: Recurrent Depth Enables In-Context Dynamics Prediction","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}