{"total":59,"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":"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":"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":"2503.10537","title":"Structured Preconditioners in Adaptive Optimization: A Unified Analysis","created":"2025-03-13","cited_by_count":33,"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":"2505.22988","title":"Model-Preserving Adaptive Rounding","created":"2025-05-29","cited_by_count":23,"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":"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":"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":"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":"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":"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":"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":"2410.00232","title":"Preconditioning for Accelerated Gradient Descent Optimization and Regularization","created":"2024-09-30","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":"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":"2602.06880","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":"2506.06606","title":"Stacey: Promoting Stochastic Steepest Descent via Accelerated $\\ell_p$-Smooth Nonconvex Optimization","created":"2025-06-07","cited_by_count":3,"area":null},{"id":"2606.11660","title":"Bergson: An Open Source Library for Data Attribution","created":"2026-06-10","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":"2412.10663","title":"Memory-Efficient 4-bit Preconditioned Stochastic Optimization","created":"2024-12-14","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":"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":"2602.03096","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":"2605.18528","title":"Tight Complexity of Muon under Heavy-Tailed Noise","created":"2026-05-18","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":"2606.20299","title":"Statistical Properties of Training & Generalization","created":"2026-06-18","cited_by_count":2,"area":null},{"id":"2509.11167","title":"Harnessing Optimization Dynamics for Curvature-Informed Model Merging","created":"2025-09-14","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":"2605.06316","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":"2606.25975","title":"Tensorion: A Tensor-Aware Generalization of the Muon Optimizer","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2607.06723","title":"Optimization Geometrodynamics: Variational Reduction and Interaction Curvature","created":"2026-07-07","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":"2609.07597","title":"Beyond the Matrix Sign: Quadratic Spectral Descent","created":"2026-09-07","cited_by_count":1,"area":null},{"id":"2511.03972","title":"Non-Asymptotic Optimization and Generalization Bounds for Stochastic Gauss-Newton in Overparameterized Models","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2605.08734","title":"AdaPreLoRA: Adafactor Preconditioned Low-Rank Adaptation","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.23391","title":"Coupling-Robust Accuracy in Multiphysics Physics Informed Neural Networks via Kronecker-Preconditioned Optimization","created":"2026-05-22","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":"2606.00542","title":"Rethinking Bregman Divergences in Kronecker-Factored Optimizers","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2609.07155","title":"Mind the Approximation: Fisher-Weighted SVD Compression for ViTs","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.12991","title":"Information-Induced Training Geometry: Exact Reduction, Canonical Completion, and Structured Expressivity","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2609.38521","title":"ShamAN-Q: Shampoo Augmented NanoQuant for Sub-1-bit LLM Weights","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.04204","title":"Clean: Second-order LLM Training at Linear Memory Cost via Nystr{\\\"o}m Sketching","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.08975","title":"The Best Optimizer Depends on Batch Size","created":"2026-10-06","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}