{"total":46,"rows":[{"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":"2601.13474","title":"Preconditioning Benefits of Spectral Orthogonalization in Muon","created":"2026-01-20","cited_by_count":30,"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":"2603.26554","title":"Sharp Capacity Scaling of Spectral Optimizers in Learning Associative Memory","created":"2026-03-27","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":"2603.09952","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":"2601.21750","title":"FISMO: Fisher-Structured Momentum-Orthogonalized Optimizer","created":"2026-01-29","cited_by_count":11,"area":null},{"id":"2603.00742","title":"To Use or not to Use Muon: How Simplicity Bias in Optimizers Matters","created":"2026-02-28","cited_by_count":10,"area":null},{"id":"2601.19400","title":"Improved Convergence Rates of Muon Optimizer for Nonconvex Optimization","created":"2026-01-27","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":"2511.11466","title":"Non-Euclidean SGD for Structured Optimization: Unified Analysis and Improved Rates","created":"2025-11-14","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":"2602.22681","title":"Accelerating LLM Pre-Training through Flat-Direction Dynamics Enhancement","created":"2026-02-26","cited_by_count":8,"area":null},{"id":"2601.22652","title":"Spectral Gradient Descent Mitigates Anisotropy-Driven Misalignment: A Case Study in Phase Retrieval","created":"2026-01-30","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":"2605.06654","title":"Optimizer-Model Consistency: Full Finetuning with the Same Optimizer as Pretraining Forgets Less","created":"2026-05-07","cited_by_count":5,"area":null},{"id":"2602.11137","title":"Weight Decay Improves Language Model Plasticity","created":"2026-02-11","cited_by_count":4,"area":null},{"id":"2604.09258","title":"Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima","created":"2026-04-10","cited_by_count":4,"area":null},{"id":"2603.06922","title":"NerVE: Nonlinear Eigenspectrum Dynamics in LLM Feed-Forward Networks","created":"2026-03-06","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":"2606.30509","title":"Muon learns balanced solutions in matrix factorization without slow saddle-to-saddle dynamics","created":"2026-06-29","cited_by_count":3,"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":"2606.03899","title":"Denoise First, Orthogonalize Later: Understanding Momentum in Muon via Spectral Filtering","created":"2026-06-02","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":"2608.07436","title":"Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers","created":"2026-08-07","cited_by_count":2,"area":null},{"id":"2605.09331","title":"Dimension-Free Saddle-Point Escape in Muon","created":"2026-05-10","cited_by_count":1,"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":"2605.29157","title":"Parallax: Parameterized Local Linear Attention for Language Modeling","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2606.06470","title":"PC Layer: Polynomial Weight Preconditioning for Improving LLM Pre-Training","created":"2026-06-04","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":"2607.13246","title":"Reassessing Muon for Matrix Factorization","created":"2026-07-14","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":"2605.09991","title":"Optimizer-Induced Mode Connectivity: From AdamW to Muon","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.17806","title":"AMO: Operator-level Adaptive Muon Orthogonalization","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.28961","title":"Dynamics of Stochastic Momentum with Sparse Updates in High Dimensions","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2607.01124","title":"Muon as a Residual Connection","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.14371","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2607.19390","title":"The Orthogonalized Read Is a Removable Training Scaffold for Recurrent Memory","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2609.32902","title":"Linger and Lose: Knowledge Collapse in Low-Bit Language Models","created":"2026-09-26","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":"2609.34915","title":"Muon Sublates the Edge of Stability in LLM Pretraining","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.02798","title":"Muon Learns Facts Better: Understanding the Role of Spectral Orthogonalization","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.10965","title":"Spectrally Targeted Muon","created":"2026-10-07","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}