{"total":67,"rows":[{"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":"2106.16225","title":"Analytic Insights into Structure and Rank of Neural Network Hessian Maps","created":"2021-06-30","cited_by_count":52,"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":"2106.08208","title":"SUPER-ADAM: Faster and Universal Framework of Adaptive Gradients","created":"2021-06-15","cited_by_count":40,"area":null},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"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":"2106.02925","title":"Tensor Normal Training for Deep Learning Models","created":"2021-06-05","cited_by_count":24,"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":"2112.02089","title":"Regularized Newton Method with Global $O(1/k^2)$ Convergence","created":"2021-12-03","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":"2402.04553","title":"Curvature-Informed SGD via General Purpose Lie-Group Preconditioners","created":"2024-02-07","cited_by_count":16,"area":null},{"id":"2106.06199","title":"LocoProp: Enhancing BackProp via Local Loss Optimization","created":"2021-06-11","cited_by_count":15,"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":"2505.02809","title":"Towards Quantifying the Hessian Structure of Neural Networks","created":"2025-05-05","cited_by_count":13,"area":null},{"id":"2510.10777","title":"Preconditioned Norms: A Unified Framework for Steepest Descent, Quasi-Newton and Adaptive Methods","created":"2025-10-12","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":"2201.10285","title":"Efficient Approximations of the Fisher Matrix in Neural Networks using Kronecker Product Singular Value Decomposition","created":"2022-01-25","cited_by_count":9,"area":null},{"id":"2412.08681","title":"Learning Physics Informed Neural ODEs With Partial Measurements","created":"2024-12-11","cited_by_count":9,"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":"2303.05473","title":"Natural Gradient Methods: Perspectives, Efficient-Scalable Approximations, and Analysis","created":"2023-03-06","cited_by_count":8,"area":null},{"id":"2106.03947","title":"TENGraD: Time-Efficient Natural Gradient Descent with Exact Fisher-Block Inversion","created":"2021-06-07","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":"2102.06737","title":"Kronecker-factored Quasi-Newton Methods for Deep Learning","created":"2021-02-12","cited_by_count":6,"area":null},{"id":"2107.03331","title":"KOALA: A Kalman Optimization Algorithm with Loss Adaptivity","created":"2021-07-07","cited_by_count":6,"area":null},{"id":"2305.00604","title":"ISAAC Newton: Input-based Approximate Curvature for Newton's Method","created":"2023-05-01","cited_by_count":6,"area":null},{"id":"2103.11154","title":"Low Dimensional Landscape Hypothesis is True: DNNs can be Trained in Tiny Subspaces","created":"2021-03-20","cited_by_count":5,"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":"2207.07287","title":"Riemannian Natural Gradient Methods","created":"2022-07-15","cited_by_count":5,"area":null},{"id":"2307.13744","title":"mL-BFGS: A Momentum-based L-BFGS for Distributed Large-Scale Neural Network Optimization","created":"2023-07-25","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":"2406.18464","title":"Bayesian inverse Navier-Stokes problems: joint flow field reconstruction and parameter learning","created":"2024-06-26","cited_by_count":4,"area":null},{"id":"2409.10777","title":"Physics-Informed Neural Networks with Trust-Region Sequential Quadratic Programming","created":"2024-09-16","cited_by_count":4,"area":null},{"id":"2109.03220","title":"Revisiting Recursive Least Squares for Training Deep Neural Networks","created":"2021-09-07","cited_by_count":3,"area":null},{"id":"2210.06171","title":"Learning to Optimize Quasi-Newton Methods","created":"2022-10-11","cited_by_count":3,"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":"2502.18153","title":"SASSHA: Sharpness-aware Adaptive Second-order Optimization with Stable Hessian Approximation","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2106.07454","title":"NG+ : A Multi-Step Matrix-Product Natural Gradient Method for Deep Learning","created":"2021-06-14","cited_by_count":2,"area":null},{"id":"2302.00347","title":"Anderson Acceleration For Bioinformatics-Based Machine Learning","created":"2023-02-01","cited_by_count":2,"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":"2402.11948","title":"Mini-Hes: A Parallelizable Second-order Latent Factor Analysis Model","created":"2024-02-19","cited_by_count":2,"area":null},{"id":"2409.07925","title":"A framework for measuring the training efficiency of a neural architecture","created":"2024-09-12","cited_by_count":2,"area":null},{"id":"2412.10663","title":"Memory-Efficient 4-bit Preconditioned Stochastic Optimization","created":"2024-12-14","cited_by_count":2,"area":null},{"id":"2502.01076","title":"qNBO: quasi-Newton Meets Bilevel Optimization","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2506.08464","title":"MAC: An Efficient Gradient Preconditioning using Mean Activation Approximated Curvature","created":"2025-06-10","cited_by_count":2,"area":null},{"id":"2605.09176","title":"Navigating LLM Valley: From AdamW to Memory-Efficient and Matrix-Based Optimizers","created":"2026-05-09","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":"2204.04718","title":"Rethinking Exponential Averaging of the Fisher","created":"2022-04-10","cited_by_count":1,"area":null},{"id":"2204.09116","title":"A Novel Fast Exact Subproblem Solver for Stochastic Quasi-Newton Cubic Regularized Optimization","created":"2022-04-19","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":"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":"2403.13128","title":"AdaFish: Fast low-rank parameter-efficient fine-tuning by using second-order information","created":"2024-03-19","cited_by_count":1,"area":null},{"id":"2405.00252","title":"Q-Newton: Hybrid Quantum-Classical Scheduling for Accelerating Neural Network Training with Newton's Gradient Descent","created":"2024-04-30","cited_by_count":1,"area":null},{"id":"2512.13728","title":"CurvaDion: Curvature-Adaptive Distributed Orthonormalization","created":"2025-12-13","cited_by_count":1,"area":null},{"id":"2103.16764","title":"Research of Damped Newton Stochastic Gradient Descent Method for Neural Network Training","created":"2021-03-31","cited_by_count":0,"area":null},{"id":"2210.12573","title":"An Efficient Nonlinear Acceleration method that Exploits Symmetry of the Hessian","created":"2022-10-22","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":"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":"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":"2408.02604","title":"Learning rheological parameters of non-Newtonian fluids from velocimetry data","created":"2024-08-05","cited_by_count":0,"area":null},{"id":"2506.08360","title":"NysAct: A Scalable Preconditioned Gradient Descent using Nystrom Approximation","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2603.20898","title":"Natural Gradient Descent for Online Continual Learning","created":"2026-03-21","cited_by_count":0,"area":null},{"id":"2605.16017","title":"Accelerated Gradient Descent for Faster Convergence with Minimal Overhead","created":"2026-05-15","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":"2610.02182","title":"SoftServe: A Scalable Quasi-Newton Method for Deep Learning","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}