{"total":75,"rows":[{"id":"2409.20325","title":"Old Optimizer, New Norm: An Anthology","created":"2024-09-30","cited_by_count":193,"area":null},{"id":"2409.11321","title":"SOAP: Improving and Stabilizing Shampoo using Adam","created":"2024-09-17","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":"2510.05491","title":"NorMuon: Making Muon more efficient and scalable","created":"2025-10-07","cited_by_count":84,"area":null},{"id":"2410.21265","title":"Modular Duality in Deep Learning","created":"2024-10-28","cited_by_count":77,"area":null},{"id":"2504.05295","title":"Dion: Distributed Orthonormalized Updates","created":"2025-04-07","cited_by_count":68,"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":"2406.17748","title":"A New Perspective on Shampoo's Preconditioner","created":"2024-06-25","cited_by_count":59,"area":null},{"id":"2503.20762","title":"ASGO: Adaptive Structured Gradient Optimization","created":"2025-03-26","cited_by_count":57,"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":"2510.16981","title":"MuonBP: Faster Muon via Block-Periodic Orthogonalization","created":"2025-10-19","cited_by_count":35,"area":null},{"id":"2410.20625","title":"LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization","created":"2024-10-27","cited_by_count":32,"area":null},{"id":"2502.15015","title":"Accelerating Neural Network Training: An Analysis of the AlgoPerf Competition","created":"2025-02-20","cited_by_count":32,"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":"2402.03496","title":"Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective","created":"2024-02-05","cited_by_count":25,"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":"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":"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":"2506.07254","title":"A Stable Whitening Optimizer for Efficient Neural Network Training","created":"2025-06-08","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":"2509.03378","title":"Understanding and Improving Shampoo and SOAP via Kullback-Leibler Minimization","created":"2025-09-03","cited_by_count":16,"area":null},{"id":"2510.25000","title":"What Really Matters in Matrix-Whitening Optimizers?","created":"2025-10-28","cited_by_count":16,"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":"2502.06761","title":"When, Where and Why to Average Weights?","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2508.06981","title":"Structure-Preserving Digital Twins via Conditional Neural Whitney Forms","created":"2025-08-09","cited_by_count":8,"area":null},{"id":"2509.26337","title":"FedMuon: Federated Learning with Bias-corrected LMO-based Optimization","created":"2025-09-30","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":"2602.09314","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":"2502.02132","title":"How Memory in Optimization Algorithms Implicitly Modifies the Loss","created":"2025-02-04","cited_by_count":6,"area":null},{"id":"2410.05021","title":"DEPT: Decoupled Embeddings for Pre-training Language Models","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2508.13898","title":"Beyond the Mean: Fisher-Orthogonal Projection for Natural Gradient Descent in Large Batch Training","created":"2025-08-19","cited_by_count":5,"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":"2402.11858","title":"Stochastic Hessian Fittings with Lie Groups","created":"2024-02-19","cited_by_count":4,"area":null},{"id":"2503.22235","title":"WeatherMesh-3: Fast and accurate operational global weather forecasting","created":"2025-03-28","cited_by_count":4,"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":"2601.22137","title":"PRISM: Distribution-free Adaptive Computation of Matrix Functions for Accelerating Neural Network Training","created":"2026-01-29","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":"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":"2605.09552","title":"Phases of Muon: When Muon Eclipses SignSGD","created":"2026-05-10","cited_by_count":3,"area":null},{"id":"2605.17109","title":"DynMuon: A Dynamic Spectral Shaping View of Muon","created":"2026-05-16","cited_by_count":3,"area":null},{"id":"2606.23357","title":"SOAP-Bubbles: Structured Weight Uncertainty for Neural Networks","created":"2026-06-22","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":"2412.10663","title":"Memory-Efficient 4-bit Preconditioned Stochastic Optimization","created":"2024-12-14","cited_by_count":2,"area":null},{"id":"2505.23337","title":"Matryoshka Model Learning for Improved Elastic Student Models","created":"2025-05-29","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":"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":"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":"2606.02365","title":"FOAM: Frequency and Operator Error-Based Adaptive Damping Method for Reducing Staleness-Oriented Error for Shampoo","created":"2026-06-01","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":"2511.06477","title":"DyKAF: Dynamical Kronecker Approximation of the Fisher Information Matrix for Gradient Preconditioning","created":"2025-11-09","cited_by_count":1,"area":null},{"id":"2601.07326","title":"Convergence Rate Analysis of the AdamW-style Shampoo: Unifying One-Sided and Two-Sided Preconditioning","created":"2026-01-12","cited_by_count":1,"area":null},{"id":"2605.04418","title":"Demystifying Manifold Constraints in LLM Pre-training","created":"2026-05-06","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":"2605.16184","title":"Runtime-Orchestrated Second-Order Optimization for Scalable LLM Training","created":"2026-05-15","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":"2607.14536","title":"Muse: Representation Geometry of Muon Beyond Normalized Momentum","created":"2026-07-16","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":"2609.04577","title":"Optimizer Memory Schedules for Outscaling the Overtraining Axis","created":"2026-09-04","cited_by_count":1,"area":null},{"id":"2310.12298","title":"Jorge: Approximate Preconditioning for GPU-efficient Second-order Optimization","created":"2023-10-18","cited_by_count":0,"area":null},{"id":"2311.10085","title":"A Computationally Efficient Sparsified Online Newton Method","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2502.06268","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2505.00982","title":"DHO$_2$: Accelerating Distributed Hybrid Order Optimization via Model Parallelism and ADMM","created":"2025-05-02","cited_by_count":0,"area":null},{"id":"2602.16456","title":"Beyond SGD, Without SVD: Proximal Subspace Iteration LoRA with Diagonal Fractional K-FAC","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2605.26327","title":"Reparametrizing Shampoo and SOAP for Subspace Basis Updates and BFloat16 Storage","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.00442","title":"Exploiting weight-space symmetries for approximating curvature","created":"2026-05-30","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":"2610.03222","title":"Near-Optimal Convex Optimization with Lazy Second-Order Oracles","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.08534","title":"How Bregman Divergences Shape Shampoo","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.13036","title":"Towards Easier-to-Tune Training Algorithms: New Results from AlgoPerf","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.16923","title":"Minimax Optimality of Shampoo for Nonstationary Stochastic Optimization","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18695","title":"A Refresh Interval Does Not Fully Specify a Refresh Schedule: Learning-Rate-Dependent Placement in Kronecker-Preconditioned Language Model Training","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}