{"total":23,"rows":[{"id":"2409.11321","title":"SOAP: Improving and Stabilizing Shampoo using Adam","created":"2024-09-17","cited_by_count":192,"area":null},{"id":"2309.06497","title":"A Distributed Data-Parallel PyTorch Implementation of the Distributed Shampoo Optimizer for Training Neural Networks At-Scale","created":"2023-09-12","cited_by_count":77,"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":"2311.00636","title":"Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures","created":"2023-11-01","cited_by_count":49,"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":"2305.04684","title":"ASDL: A Unified Interface for Gradient Preconditioning in PyTorch","created":"2023-05-08","cited_by_count":21,"area":null},{"id":"2406.06420","title":"An Improved Empirical Fisher Approximation for Natural Gradient Descent","created":"2024-06-10","cited_by_count":15,"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":"2302.11147","title":"Stochastic Approximation Beyond Gradient for Signal Processing and Machine Learning","created":"2023-02-22","cited_by_count":10,"area":null},{"id":"2402.05379","title":"Trade-Offs of Diagonal Fisher Information Matrix Estimators","created":"2024-02-08","cited_by_count":10,"area":null},{"id":"2202.04124","title":"A Mini-Block Fisher Method for Deep Neural Networks","created":"2022-02-08","cited_by_count":8,"area":null},{"id":"2407.10780","title":"Correlations Are Ruining Your Gradient Descent","created":"2024-07-15","cited_by_count":7,"area":null},{"id":"2505.23737","title":"On the Convergence Analysis of Muon","created":"2025-05-29","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":"2305.19416","title":"KrADagrad: Kronecker Approximation-Domination Gradient Preconditioned Stochastic Optimization","created":"2023-05-30","cited_by_count":3,"area":null},{"id":"2310.14963","title":"Studying K-FAC Heuristics by Viewing Adam through a Second-Order Lens","created":"2023-10-23","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":"2308.02123","title":"Eva: A General Vectorized Approximation Framework for Second-order Optimization","created":"2023-08-04","cited_by_count":1,"area":null},{"id":"2312.03885","title":"Gathering and Exploiting Higher-Order Information when Training Large Structured Models","created":"2023-12-06","cited_by_count":1,"area":null},{"id":"2305.13664","title":"Layer-wise Adaptive Step-Sizes for Stochastic First-Order Methods for Deep Learning","created":"2023-05-23","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}],"next_cursor":null}