{"total":77,"rows":[{"id":"2502.07529","title":"Training Deep Learning Models with Norm-Constrained LMOs","created":"2025-02-11","cited_by_count":192,"area":null},{"id":"2505.16932","title":"The Polar Express: Optimal Matrix Sign Methods and Their Application to the Muon Algorithm","created":"2025-05-22","cited_by_count":110,"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":"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":"2511.00674","title":"Isotropic Curvature Model for Understanding Deep Learning Optimization: Is Gradient Orthogonalization Optimal?","created":"2025-11-01","cited_by_count":37,"area":null},{"id":"2510.16981","title":"MuonBP: Faster Muon via Block-Periodic Orthogonalization","created":"2025-10-19","cited_by_count":35,"area":null},{"id":"2503.10537","title":"Structured Preconditioners in Adaptive Optimization: A Unified Analysis","created":"2025-03-13","cited_by_count":33,"area":null},{"id":"2502.17410","title":"COSMOS: A Hybrid Adaptive Optimizer for Memory-Efficient Training of LLMs","created":"2025-02-24","cited_by_count":30,"area":null},{"id":"2601.13474","title":"Preconditioning Benefits of Spectral Orthogonalization in Muon","created":"2026-01-20","cited_by_count":30,"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":"2510.27403","title":"FedMuon: Accelerating Federated Learning with Matrix Orthogonalization","created":"2025-10-31","cited_by_count":16,"area":null},{"id":"2506.16659","title":"Memory-Efficient LLM Pretraining via Minimalist Optimizer Design","created":"2025-06-20","cited_by_count":13,"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":"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":"2603.10067","title":"HTMuon: Improving Muon via Heavy-Tailed Spectral Correction","created":"2026-03-10","cited_by_count":12,"area":null},{"id":"2509.23106","title":"Effective Quantization of Muon Optimizer States","created":"2025-09-27","cited_by_count":11,"area":null},{"id":"2510.10777","title":"Preconditioned Norms: A Unified Framework for Steepest Descent, Quasi-Newton and Adaptive Methods","created":"2025-10-12","cited_by_count":11,"area":null},{"id":"2506.04430","title":"Leveraging Coordinate Momentum in SignSGD and Muon: Memory-Optimized Zero-Order","created":"2025-06-04","cited_by_count":9,"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":"2510.19376","title":"Optimization Benchmark for Diffusion Models on Dynamical Systems","created":"2025-10-22","cited_by_count":7,"area":"diffusion"},{"id":"2602.08040","title":"FIRE: Frobenius-Isometry Reinitialization for Balancing the Stability-Plasticity Tradeoff","created":"2026-02-08","cited_by_count":7,"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":"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":"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":"2605.12492","title":"Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation","created":"2026-05-12","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":"2512.17131","title":"Smoothing DiLoCo with Primal Averaging for Faster Training of LLMs","created":"2025-12-18","cited_by_count":5,"area":null},{"id":"2603.26661","title":"GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation","created":"2026-03-27","cited_by_count":5,"area":"diffusion"},{"id":"2605.08949","title":"Muon-OGD: Muon-based Spectral Orthogonal Gradient Projection for LLM Continual Learning","created":"2026-05-09","cited_by_count":5,"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":"2507.08091","title":"Low-rank Momentum Factorization for Memory Efficient Training","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2602.05943","title":"Orthogonal Model Merging","created":"2026-02-05","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":"2603.03597","title":"NuMuon: Nuclear-Norm-Constrained Muon for Compressible LLM Training","created":"2026-03-04","cited_by_count":4,"area":null},{"id":"2606.04058","title":"Spectral Scaling Laws of Muon","created":"2026-06-02","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":"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":"2509.15874","title":"ENSAM: an efficient foundation model for interactive segmentation of 3D medical images","created":"2025-09-19","cited_by_count":2,"area":null},{"id":"2602.03001","title":"Adaptive Batch Sizes Using Non-Euclidean Gradient Noise Scales for Stochastic Sign and Spectral Descent","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2604.07372","title":"NS-RGS: Newton-Schulz based Riemannian gradient method for orthogonal group synchronization","created":"2026-04-07","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":"2606.29176","title":"Dead-Direction Conditioners: Gauge-Equivariant Preconditioning for Deep Networks","created":"2026-06-28","cited_by_count":2,"area":null},{"id":"2607.17620","title":"PoLoRA: A Preconditioned Orthogonalized LoRA Optimizer","created":"2026-07-20","cited_by_count":2,"area":null},{"id":"2505.13397","title":"Learning by solving differential equations","created":"2025-05-19","cited_by_count":1,"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":"2605.26929","title":"When Muon Optimizer Meets Adversarial Training: A Theoretical and Empirical Study","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2606.25342","title":"Lifelong In-Context Learning with Transformers Requires Parametric Forms of Attention","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2607.01455","title":"Ember: A Kilobyte-State Optimizer for Token Interfaces","created":"2026-07-01","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":"2607.26001","title":"Sharpness-Aware Minimization and Muon: Robustness under the Spectral Norm","created":"2026-07-28","cited_by_count":1,"area":null},{"id":"2608.14492","title":"Approximate Muon with low-rank adapters","created":"2026-08-14","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":"2605.05577","title":"Accelerating LMO-Based Optimization via Implicit Gradient Transport","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.16341","title":"Orth-Dion: Eliminating Geometric Mismatch in Distributed Low-Rank Spectral Optimization","created":"2026-05-07","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":"2606.24134","title":"Uniform Sampling from High-dimensional Spectral Norm Balls","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2608.02991","title":"Control Allocation in Neural Network Optimization: Joint Affine Control of Weight and Bias Updates","created":"2026-08-04","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":"2609.09676","title":"Muon-C: Operator-Aligned Muon for Convolutional Kernels","created":"2026-09-09","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":"2609.32861","title":"Muon Under Gradient Noise and the Limits of Orthogonalization Near Optima","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.39114","title":"The Row Normalization Puzzle in Muon","created":"2026-09-30","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":"2610.03306","title":"Training-Loss Guarantees for Muon with Finite-Step Newton--Schulz Orthogonalization","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.13773","title":"Geometry-Aware Multi-Objective Optimization: Norm-Constrained Oracles with Entropic Weight Updates","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.16868","title":"From Parallel to Sequential: Small-Batch Noise Restores Simplicity Bias of Muon","created":"2026-10-12","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}],"next_cursor":null}