{"total":178,"rows":[{"id":"2510.05491","title":"NorMuon: Making Muon more efficient and scalable","created":"2025-10-07","cited_by_count":84,"area":null},{"id":"2505.02222","title":"Practical Efficiency of Muon for Pretraining","created":"2025-05-04","cited_by_count":80,"area":null},{"id":"2411.10438","title":"MARS: Unleashing the Power of Variance Reduction for Training Large Models","created":"2024-11-15","cited_by_count":64,"area":null},{"id":"2503.20762","title":"ASGO: Adaptive Structured Gradient Optimization","created":"2025-03-26","cited_by_count":57,"area":null},{"id":"2502.00604","title":"Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization Perspective","created":"2025-02-02","cited_by_count":56,"area":null},{"id":"2503.02113","title":"Deep Learning is Not So Mysterious or Different","created":"2025-03-03","cited_by_count":56,"area":null},{"id":"2411.16085","title":"Cautious Optimizers: Improving Training with One Line of Code","created":"2024-11-25","cited_by_count":47,"area":null},{"id":"2505.13738","title":"Power Lines: Scaling Laws for Weight Decay and Batch Size in LLM Pre-training","created":"2025-05-19","cited_by_count":43,"area":null},{"id":"2502.04664","title":"Implicit Bias of Spectral Descent and Muon on Multiclass Separable Data","created":"2025-02-07","cited_by_count":41,"area":null},{"id":"2506.04192","title":"Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise","created":"2025-06-04","cited_by_count":41,"area":null},{"id":"2507.07101","title":"Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation Is Wasteful","created":"2025-07-09","cited_by_count":41,"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":"2601.19156","title":"Convergence of Muon with Newton-Schulz","created":"2026-01-27","cited_by_count":36,"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":"2502.19002","title":"The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training","created":"2025-02-26","cited_by_count":30,"area":null},{"id":"2506.03595","title":"Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its Preconditioner","created":"2025-06-04","cited_by_count":23,"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":"2512.05620","title":"Hyperparameter Transfer Enables Consistent Gains of Matrix-Preconditioned Optimizers Across Scales","created":"2025-12-05","cited_by_count":21,"area":null},{"id":"2412.13148","title":"SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training","created":"2024-12-17","cited_by_count":20,"area":null},{"id":"2410.15608","title":"Moonshine: Speech Recognition for Live Transcription and Voice Commands","created":"2024-10-21","cited_by_count":19,"area":null},{"id":"2505.24749","title":"SUMO: Subspace-Aware Moment-Orthogonalization for Accelerating Memory-Efficient LLM Training","created":"2025-05-30","cited_by_count":19,"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":"2604.01472","title":"The Newton-Muon Optimizer","created":"2026-04-01","cited_by_count":18,"area":null},{"id":"2510.09378","title":"The Potential of Second-Order Optimization for LLMs: A Study with Full Gauss-Newton","created":"2025-10-10","cited_by_count":17,"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":"2507.08972","title":"Simulating Three-dimensional Turbulence with Physics-informed Neural Networks","created":"2025-07-11","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":"2503.07667","title":"CLIMB: Data Foundations for Large Scale Multimodal Clinical Foundation Models","created":"2025-03-09","cited_by_count":13,"area":null},{"id":"2505.02809","title":"Towards Quantifying the Hessian Structure of Neural Networks","created":"2025-05-05","cited_by_count":13,"area":null},{"id":"2506.19697","title":"Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models","created":"2025-06-24","cited_by_count":13,"area":null},{"id":"2506.23803","title":"SGD with Adaptive Preconditioning: Unified Analysis and Momentum Acceleration","created":"2025-06-30","cited_by_count":12,"area":null},{"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":"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":"2601.21750","title":"FISMO: Fisher-Structured Momentum-Orthogonalized Optimizer","created":"2026-01-29","cited_by_count":11,"area":null},{"id":"2603.14315","title":"Enhancing LLM Training via Spectral Clipping","created":"2026-03-15","cited_by_count":10,"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":"2506.08001","title":"Reparameterized LLM Training via Orthogonal Equivalence Transformation","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2509.25087","title":"Scaling with Collapse: Efficient and Predictable Training of LLM Families","created":"2025-09-29","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":"2505.24275","title":"GradPower: Powering Gradients for Faster Language Model Pre-Training","created":"2025-05-30","cited_by_count":8,"area":null},{"id":"2510.15830","title":"SNOO: Step-K Nesterov Outer Optimizer - The Surprising Effectiveness of Nesterov Momentum Applied to Pseudo-Gradients","created":"2025-10-17","cited_by_count":8,"area":null},{"id":"2602.02788","title":"Structure-Preserving Learning Improves Geometry Generalization in Neural PDEs","created":"2026-02-02","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":"2605.06884","title":"Muon with Nesterov Momentum: Heavy-Tailed Noise and (Randomized) Inexact Polar Decomposition","created":"2026-05-07","cited_by_count":8,"area":null},{"id":"2507.01649","title":"GradMetaNet: An Equivariant Architecture for Learning on Gradients","created":"2025-07-02","cited_by_count":7,"area":null},{"id":"2512.21319","title":"Variationally correct operator learning: Reduced basis neural operator with a posteriori error estimation","created":"2025-12-24","cited_by_count":7,"area":null},{"id":"2602.04774","title":"Theory of Optimal Learning Rate Schedules and Scaling Laws for a Random Feature Model","created":"2026-02-04","cited_by_count":7,"area":null},{"id":"2602.15322","title":"On Surprising Effectiveness of Masking Updates in Adaptive Optimizers","created":"2026-02-17","cited_by_count":7,"area":null},{"id":"2601.23261","title":"TEON: Tensorized Orthonormalization Beyond Layer-Wise Muon for Large Language Model Pre-Training","created":"2026-01-30","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":"2605.10797","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":"2505.23737","title":"On the Convergence Analysis of Muon","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2509.24218","title":"Conda: Column-Normalized Adam for Training Large Language Models Faster","created":"2025-09-29","cited_by_count":5,"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":"2603.01514","title":"Training Dynamics of Softmax Self-Attention: Fast Global Convergence via Preconditioning","created":"2026-03-02","cited_by_count":5,"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":"2412.17107","title":"Grams: Gradient Descent with Adaptive Momentum Scaling","created":"2024-12-22","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":"2602.06079","title":"Canzona: A Unified, Asynchronous, and Load-Balanced Framework for Distributed Matrix-based Optimizers","created":"2026-02-04","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":"2602.19271","title":"Taming Preconditioner Drift: Unlocking the Potential of Second-Order Optimizers for Federated Learning on Non-IID Data","created":"2026-02-22","cited_by_count":4,"area":null},{"id":"2603.17970","title":"Beyond Muon: MUD (MomentUm Decorrelation) for Faster Transformer Training","created":"2026-03-18","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":"2508.00180","title":"EMA Without the Lag: Bias-Corrected Iterate Averaging Schemes","created":"2025-07-31","cited_by_count":3,"area":null},{"id":"2508.11281","title":"ToxiFrench: Benchmarking and Enhancing Language Models via CoT Fine-Tuning for French Toxicity Detection","created":"2025-08-15","cited_by_count":3,"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":"2510.23804","title":"How do simple rotations affect the implicit bias of Adam?","created":"2025-10-27","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":"2606.27153","title":"DMuon: Efficient Distributed Muon Training with Near-Adam Overhead","created":"2026-06-25","cited_by_count":3,"area":null},{"id":"2607.02499","title":"Beyond Adam: SOAP and Muon for Faster, Label-Efficient Training of Machine Learning Interatomic Potentials","created":"2026-07-02","cited_by_count":3,"area":null},{"id":"2411.07120","title":"Lean and Mean Adaptive Optimization via Subset-Norm and Subspace-Momentum with Convergence Guarantees","created":"2024-11-11","cited_by_count":2,"area":null},{"id":"2412.10663","title":"Memory-Efficient 4-bit Preconditioned Stochastic Optimization","created":"2024-12-14","cited_by_count":2,"area":null},{"id":"2506.01049","title":"Taming LLMs by Scaling Learning Rates with Gradient Grouping","created":"2025-06-01","cited_by_count":2,"area":null},{"id":"2509.22938","title":"Understanding SOAP from the Perspective of Gradient Whitening","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2509.25380","title":"Predicting Training Re-evaluation Curves Enables Effective Data Curriculums for LLMs","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2510.13680","title":"Adam or Gauss-Newton? A Comparative Study In Terms of Basis Alignment and SGD Noise","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2601.20769","title":"Leveraging Second-Order Curvature for Efficient Learned Image Compression: Theory and Empirical Evidence","created":"2026-01-28","cited_by_count":2,"area":null},{"id":"2602.02016","title":"DASH: Faster Shampoo via Batched Block Preconditioning and Efficient Inverse-Root Solvers","created":"2026-02-02","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":"2602.03096","title":"PRISM: Structured Optimization via Anisotropic Spectral Shaping","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2602.03515","title":"Mitigating Staleness in Asynchronous Pipeline Parallelism via Basis Rotation","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2602.04201","title":"From Sparse Sensors to Continuous Fields: STRIDE for Spatiotemporal Reconstruction","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2604.09543","title":"ANTIC: Adaptive Neural Temporal In-situ Compressor","created":"2026-04-10","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":"2604.23528","title":"When PINNs Go Wrong: Pseudo-Time Stepping Against Spurious Solutions","created":"2026-04-26","cited_by_count":2,"area":null},{"id":"2605.11838","title":"Gradient Clipping Beyond Vector Norms: A Spectral Approach for Matrix-Valued Parameters","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2605.16165","title":"Second-Order Multi-Level Variance Correction for Modality Competition in Multimodal Models","created":"2026-05-15","cited_by_count":2,"area":null},{"id":"2605.24651","title":"WINO: A Weak-Form Physics Informed Neural Operator for Hyperelasticity on Variable Domains","created":"2026-05-23","cited_by_count":2,"area":null},{"id":"2606.19179","title":"Compute Efficiency and Serial Runtime Tradeoffs for Stochastic Momentum Methods","created":"2026-06-17","cited_by_count":2,"area":null}],"next_cursor":"100"}