{"total":37,"rows":[{"id":"2409.11321","title":"SOAP: Improving and Stabilizing Shampoo using Adam","created":"2024-09-17","cited_by_count":192,"area":null},{"id":"2109.14119","title":"Stochastic Training is Not Necessary for Generalization","created":"2021-09-29","cited_by_count":63,"area":null},{"id":"2406.17748","title":"A New Perspective on Shampoo's Preconditioner","created":"2024-06-25","cited_by_count":59,"area":null},{"id":"2107.03356","title":"M-FAC: Efficient Matrix-Free Approximations of Second-Order Information","created":"2021-07-07","cited_by_count":54,"area":null},{"id":"2201.12250","title":"Gradient Descent on Neurons and its Link to Approximate Second-Order Optimization","created":"2022-01-28","cited_by_count":30,"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":"2211.14133","title":"PipeFisher: Efficient Training of Large Language Models Using Pipelining and Fisher Information Matrices","created":"2022-11-25","cited_by_count":24,"area":null},{"id":"2102.07405","title":"Tractable structured natural gradient descent using local parameterizations","created":"2021-02-15","cited_by_count":22,"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":"2107.01739","title":"KAISA: An Adaptive Second-Order Optimizer Framework for Deep Neural Networks","created":"2021-07-04","cited_by_count":20,"area":null},{"id":"2106.02624","title":"ViViT: Curvature access through the generalized Gauss-Newton's low-rank structure","created":"2021-06-04","cited_by_count":16,"area":null},{"id":"2209.06979","title":"Efficient Quantized Sparse Matrix Operations on Tensor Cores","created":"2022-09-14","cited_by_count":16,"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":"2102.08431","title":"Complex Momentum for Optimization in Games","created":"2021-02-16","cited_by_count":11,"area":null},{"id":"2111.00856","title":"Large-Scale Deep Learning Optimizations: A Comprehensive Survey","created":"2021-11-01","cited_by_count":10,"area":null},{"id":"2306.03968","title":"Stochastic Marginal Likelihood Gradients using Neural Tangent Kernels","created":"2023-06-06","cited_by_count":10,"area":null},{"id":"2206.15143","title":"Scalable K-FAC Training for Deep Neural Networks with Distributed Preconditioning","created":"2022-06-30","cited_by_count":7,"area":null},{"id":"2306.01685","title":"MKOR: Momentum-Enabled Kronecker-Factor-Based Optimizer Using Rank-1 Updates","created":"2023-06-02","cited_by_count":7,"area":null},{"id":"2306.06098","title":"Error Feedback Can Accurately Compress Preconditioners","created":"2023-06-09","cited_by_count":6,"area":null},{"id":"2107.06533","title":"Accelerating Distributed K-FAC with Smart Parallelism of Computing and Communication Tasks","created":"2021-07-14","cited_by_count":5,"area":null},{"id":"2403.06425","title":"A Differential Geometric View and Explainability of GNN on Evolving Graphs","created":"2024-03-11","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":"2210.12184","title":"A New Perspective for Understanding Generalization Gap of Deep Neural Networks Trained with Large Batch Sizes","created":"2022-10-21","cited_by_count":3,"area":null},{"id":"2602.17385","title":"Dataless Weight Disentanglement in Task Arithmetic via Kronecker-Factored Approximate Curvature","created":"2026-02-19","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":"2410.14325","title":"Debiasing Mini-Batch Quadratics for Applications in Deep Learning","created":"2024-10-18","cited_by_count":2,"area":null},{"id":"2104.01948","title":"Robust Trust Region for Weakly Supervised Segmentation","created":"2021-04-05","cited_by_count":1,"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":"2603.29108","title":"Efficient Bilevel Optimization with KFAC-Based Hypergradients","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2605.09331","title":"Dimension-Free Saddle-Point Escape in Muon","created":"2026-05-10","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":"2208.02017","title":"Neural Nets with a Newton Conjugate Gradient Method on Multiple GPUs","created":"2022-08-03","cited_by_count":0,"area":null},{"id":"2302.13536","title":"Natural Gradient Hybrid Variational Inference with Application to Deep Mixed Models","created":"2023-02-27","cited_by_count":0,"area":null},{"id":"2303.18083","title":"Analysis and Comparison of Two-Level KFAC Methods for Training Deep Neural Networks","created":"2023-03-31","cited_by_count":0,"area":null},{"id":"2306.04004","title":"Randomized Schur Complement Views for Graph Contrastive Learning","created":"2023-06-06","cited_by_count":0,"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":"2603.25976","title":"Second-Order, First-Class: A Composable Stack for Curvature-Aware Training","created":"2026-03-26","cited_by_count":0,"area":null}],"next_cursor":null}