{"total":46,"rows":[{"id":"2409.11321","title":"SOAP: Improving and Stabilizing Shampoo using Adam","created":"2024-09-17","cited_by_count":192,"area":null},{"id":"2502.07529","title":"Training Deep Learning Models with Norm-Constrained LMOs","created":"2025-02-11","cited_by_count":192,"area":null},{"id":"2202.00089","title":"Understanding AdamW through Proximal Methods and Scale-Freeness","created":"2022-01-31","cited_by_count":46,"area":null},{"id":"2106.04881","title":"Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms","created":"2021-06-09","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":"2305.04684","title":"ASDL: A Unified Interface for Gradient Preconditioning in PyTorch","created":"2023-05-08","cited_by_count":21,"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":"2506.07254","title":"A Stable Whitening Optimizer for Efficient Neural Network Training","created":"2025-06-08","cited_by_count":18,"area":null},{"id":"2402.04553","title":"Curvature-Informed SGD via General Purpose Lie-Group Preconditioners","created":"2024-02-07","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":"2312.12226","title":"On the Parameterization of Second-Order Optimization Effective Towards the Infinite Width","created":"2023-12-19","cited_by_count":15,"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":"2411.01803","title":"Gradient Methods with Online Scaling","created":"2024-11-04","cited_by_count":11,"area":null},{"id":"2211.04422","title":"Black Box Lie Group Preconditioners for SGD","created":"2022-11-08","cited_by_count":9,"area":null},{"id":"2502.14172","title":"A Finite Sample Analysis of Distributional TD Learning with Linear Function Approximation","created":"2025-02-20","cited_by_count":6,"area":null},{"id":"2509.23500","title":"Beyond Outliers: A Study of Optimizers Under Quantization","created":"2025-09-27","cited_by_count":6,"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":"2402.08784","title":"Preconditioners for the Stochastic Training of Neural Fields","created":"2024-02-13","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":"2403.12188","title":"PETScML: Second-order solvers for training regression problems in Scientific Machine Learning","created":"2024-03-18","cited_by_count":4,"area":null},{"id":"2503.12912","title":"Pose as a Modality: A Psychology-Inspired Network for Personality Recognition with a New Multimodal Dataset","created":"2025-03-17","cited_by_count":4,"area":null},{"id":"2507.15290","title":"Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdown","created":"2025-07-21","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":"2403.08585","title":"Improving Implicit Regularization of SGD with Preconditioning for Least Square Problems","created":"2024-03-13","cited_by_count":3,"area":null},{"id":"2212.08769","title":"Improving Levenberg-Marquardt Algorithm for Neural Networks","created":"2022-12-17","cited_by_count":2,"area":null},{"id":"2502.10784","title":"Preconditioned Inexact Stochastic ADMM for Deep Model","created":"2025-02-15","cited_by_count":2,"area":null},{"id":"2507.17748","title":"Large Learning Rates Simultaneously Achieve Robustness to Spurious Correlations and Compressibility","created":"2025-07-23","cited_by_count":2,"area":null},{"id":"2511.19716","title":"Design Criteria for SGD Preconditioners: Local Conditioning, Noise Floors, and Basin Stability","created":"2025-11-24","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":"2105.02062","title":"Understanding Short-Range Memory Effects in Deep Neural Networks","created":"2021-05-05","cited_by_count":1,"area":null},{"id":"2210.11275","title":"Causal Structural Hypothesis Testing and Data Generation Models","created":"2022-10-20","cited_by_count":1,"area":null},{"id":"2302.08484","title":"FOSI: Hybrid First and Second Order Optimization","created":"2023-02-16","cited_by_count":1,"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":"2603.10485","title":"Dual Space Preconditioning for Gradient Descent in the Overparameterized Regime","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2605.06081","title":"Fast Gauss-Newton for Multiclass Cross-Entropy","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.11850","title":"Constrained Stochastic Spectral Preconditioning Converges for Nonconvex Objectives","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.19781","title":"From SGD to Muon: Adaptive Optimization via Schatten-p Norms","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.27541","title":"SparseOpt: Addressing Normalization-induced Gradient Skew in Sparse Training","created":"2026-05-26","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":"2606.15725","title":"Score-Based Martingale Posteriors for Deep Neural Networks","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2610.02182","title":"SoftServe: A Scalable Quasi-Newton Method for Deep Learning","created":"2026-10-01","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":"2610.13036","title":"Towards Easier-to-Tune Training Algorithms: New Results from AlgoPerf","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}