{"total":68,"rows":[{"id":"2211.07937","title":"An Improved Analysis of (Variance-Reduced) Policy Gradient and Natural Policy Gradient Methods","created":"2022-11-15","cited_by_count":68,"area":null},{"id":"2210.01400","title":"Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies","created":"2022-10-04","cited_by_count":46,"area":null},{"id":"2101.08366","title":"Quadratic Residual Networks: A New Class of Neural Networks for Solving Forward and Inverse Problems in Physics Involving PDEs","created":"2021-01-20","cited_by_count":43,"area":null},{"id":"2306.03824","title":"Understanding Generalization of Federated Learning via Stability: Heterogeneity Matters","created":"2023-06-06","cited_by_count":27,"area":null},{"id":"2106.02925","title":"Tensor Normal Training for Deep Learning Models","created":"2021-06-05","cited_by_count":24,"area":null},{"id":"2111.05326","title":"The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learning","created":"2021-11-09","cited_by_count":23,"area":null},{"id":"2311.05808","title":"Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstruction","created":"2023-11-10","cited_by_count":21,"area":null},{"id":"2109.12519","title":"AsySQN: Faster Vertical Federated Learning Algorithms with Better Computation Resource Utilization","created":"2021-09-26","cited_by_count":16,"area":null},{"id":"2110.14109","title":"Eigencurve: Optimal Learning Rate Schedule for SGD on Quadratic Objectives with Skewed Hessian Spectrums","created":"2021-10-27","cited_by_count":15,"area":null},{"id":"2303.07271","title":"Provably Convergent Plug-and-Play Quasi-Newton Methods","created":"2023-03-09","cited_by_count":15,"area":null},{"id":"2210.06635","title":"A Bayesian Optimization Framework for Finding Local Optima in Expensive Multi-Modal Functions","created":"2022-10-13","cited_by_count":12,"area":null},{"id":"2107.07572","title":"Globally Convergent Multilevel Training of Deep Residual Networks","created":"2021-07-15","cited_by_count":11,"area":null},{"id":"2411.18376","title":"Preserving Deep Representations In One-Shot Pruning: A Hessian-Free Second-Order Optimization Framework","created":"2024-11-27","cited_by_count":11,"area":null},{"id":"2211.01357","title":"Quasi-Newton Steps for Efficient Online Exp-Concave Optimization","created":"2022-11-02","cited_by_count":10,"area":null},{"id":"2405.14402","title":"Exact Gauss-Newton Optimization for Training Deep Neural Networks","created":"2024-05-23","cited_by_count":10,"area":null},{"id":"2507.14740","title":"Better Training Data Attribution via Better Inverse Hessian-Vector Products","created":"2025-07-19","cited_by_count":10,"area":null},{"id":"2306.02527","title":"Searching for Optimal Per-Coordinate Step-sizes with Multidimensional Backtracking","created":"2023-06-05","cited_by_count":9,"area":null},{"id":"2407.02772","title":"Gradient descent with generalized Newton's method","created":"2024-07-03","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":"2110.01543","title":"Stochastic Anderson Mixing for Nonconvex Stochastic Optimization","created":"2021-10-04","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":"2109.14002","title":"slimTrain -- A Stochastic Approximation Method for Training Separable Deep Neural Networks","created":"2021-09-28","cited_by_count":6,"area":null},{"id":"2304.06803","title":"Sample Average Approximation for Black-Box VI","created":"2023-04-13","cited_by_count":6,"area":null},{"id":"2207.07287","title":"Riemannian Natural Gradient Methods","created":"2022-07-15","cited_by_count":5,"area":null},{"id":"2110.08577","title":"Nys-Newton: Nystr\\\"om-Approximated Curvature for Stochastic Optimization","created":"2021-10-16","cited_by_count":4,"area":null},{"id":"2310.02581","title":"Online Estimation and Inference for Robust Policy Evaluation in Reinforcement Learning","created":"2023-10-04","cited_by_count":4,"area":null},{"id":"2403.02833","title":"SOFIM: Stochastic Optimization Using Regularized Fisher Information Matrix","created":"2024-03-05","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":"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":"2206.09576","title":"FedSSO: A Federated Server-Side Second-Order Optimization Algorithm","created":"2022-06-20","cited_by_count":3,"area":null},{"id":"2401.10923","title":"Online estimation of the inverse of the Hessian for stochastic optimization with application to universal stochastic Newton algorithms","created":"2024-01-15","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":"2507.09782","title":"Physics-informed neural networks for high-dimensional solutions and snaking bifurcations in nonlinear lattices","created":"2025-07-13","cited_by_count":3,"area":null},{"id":"2101.00218","title":"An iterative K-FAC algorithm for Deep Learning","created":"2021-01-01","cited_by_count":2,"area":null},{"id":"2104.02865","title":"Quasi-Newton Quasi-Monte Carlo for variational Bayes","created":"2021-04-07","cited_by_count":2,"area":null},{"id":"2106.05445","title":"Exploiting Local Convergence of Quasi-Newton Methods Globally: Adaptive Sample Size Approach","created":"2021-06-10","cited_by_count":2,"area":null},{"id":"2106.05809","title":"Simple Graph Convolutional Networks","created":"2021-06-10","cited_by_count":2,"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":"2205.12549","title":"Learning from time-dependent streaming data with online stochastic algorithms","created":"2022-05-25","cited_by_count":2,"area":null},{"id":"2211.15310","title":"Stochastic Steffensen method","created":"2022-11-28","cited_by_count":2,"area":null},{"id":"2402.02359","title":"Incremental Quasi-Newton Methods with Faster Superlinear Convergence Rates","created":"2024-02-04","cited_by_count":2,"area":null},{"id":"2410.19055","title":"Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms","created":"2024-10-24","cited_by_count":2,"area":null},{"id":"2509.16822","title":"Looking in the mirror: A faithful counterfactual explanation method for interpreting deep image classification models","created":"2025-09-20","cited_by_count":2,"area":null},{"id":"2111.14761","title":"Adaptive First- and Second-Order Algorithms for Large-Scale Machine Learning","created":"2021-11-29","cited_by_count":1,"area":null},{"id":"2201.13387","title":"L-SVRG and L-Katyusha with Adaptive Sampling","created":"2022-01-31","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":"2205.09121","title":"On the efficiency of Stochastic Quasi-Newton Methods for Deep Learning","created":"2022-05-18","cited_by_count":1,"area":null},{"id":"2209.11944","title":"Communication-Efficient {Federated} Learning Using Censored Heavy Ball Descent","created":"2022-09-24","cited_by_count":1,"area":null},{"id":"2305.17283","title":"Sharpened Lazy Incremental Quasi-Newton Method","created":"2023-05-26","cited_by_count":1,"area":null},{"id":"2403.09429","title":"VISA: Variational Inference with Sequential Sample-Average Approximations","created":"2024-03-14","cited_by_count":1,"area":null},{"id":"2403.12206","title":"Useful Compact Representations for Data-Fitting","created":"2024-03-18","cited_by_count":1,"area":null},{"id":"2403.15244","title":"A Stochastic Quasi-Newton Method for Non-convex Optimization with Non-uniform Smoothness","created":"2024-03-22","cited_by_count":1,"area":null},{"id":"2505.21721","title":"Nearly Dimension-Independent Convergence of Mean-Field Black-Box Variational Inference","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2604.13806","title":"Robust Ultra Low-Bit Post-Training Quantization via Stable Diagonal Curvature Estimate","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2111.07058","title":"Bolstering Stochastic Gradient Descent with Model Building","created":"2021-11-13","cited_by_count":0,"area":null},{"id":"2208.11075","title":"A Stochastic Variance Reduced Gradient using Barzilai-Borwein Techniques as Second Order Information","created":"2022-08-23","cited_by_count":0,"area":null},{"id":"2305.07484","title":"Online Learning Under A Separable Stochastic Approximation Framework","created":"2023-05-12","cited_by_count":0,"area":null},{"id":"2307.11684","title":"Minibatching Offers Improved Generalization Performance for Second Order Optimizers","created":"2023-05-26","cited_by_count":0,"area":null},{"id":"2308.10154","title":"Adaptive pruning-based Newton's method for distributed learning","created":"2023-08-20","cited_by_count":0,"area":null},{"id":"2311.16860","title":"Data-efficient operator learning for solving high Mach number fluid flow problems","created":"2023-11-28","cited_by_count":0,"area":null},{"id":"2403.08378","title":"An Adaptive Cost-Sensitive Learning and Recursive Denoising Framework for Imbalanced SVM Classification","created":"2024-03-13","cited_by_count":0,"area":null},{"id":"2508.13639","title":"Explainable Learning Rate Regimes for Stochastic Optimization","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2512.01790","title":"An hybrid stochastic Newton algorithm for logistic regression","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2601.18546","title":"Information Hidden in Gradients of Regression with Target Noise","created":"2026-01-26","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},{"id":"2605.16017","title":"Accelerated Gradient Descent for Faster Convergence with Minimal Overhead","created":"2026-05-15","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":"2610.13789","title":"Randomized Momentum Transport with Cheap Predictors","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}