{"total":18,"rows":[{"id":"2109.11926","title":"Sinkhorn Distributionally Robust Optimization","created":"2021-09-24","cited_by_count":38,"area":null},{"id":"2102.06862","title":"Wasserstein Proximal of GANs","created":"2021-02-13","cited_by_count":15,"area":null},{"id":"2211.02105","title":"Geometry and convergence of natural policy gradient methods","created":"2022-11-03","cited_by_count":12,"area":null},{"id":"2206.15273","title":"Invariance Properties of the Natural Gradient in Overparametrised Systems","created":"2022-06-30","cited_by_count":11,"area":null},{"id":"2302.13163","title":"Achieving High Accuracy with PINNs via Energy Natural Gradients","created":"2023-02-25","cited_by_count":10,"area":null},{"id":"2202.06236","title":"Efficient Natural Gradient Descent Methods for Large-Scale PDE-Based Optimization Problems","created":"2022-02-13","cited_by_count":7,"area":null},{"id":"2406.04527","title":"Generative Assignment Flows for Representing and Learning Joint Distributions of Discrete Data","created":"2024-06-06","cited_by_count":6,"area":null},{"id":"2111.11542","title":"Depth Without the Magic: Inductive Bias of Natural Gradient Descent","created":"2021-11-22","cited_by_count":5,"area":null},{"id":"2101.01162","title":"Transport information Bregman divergences","created":"2021-01-04","cited_by_count":3,"area":null},{"id":"2202.06232","title":"Generalized Tangent Kernel: A Unified Geometric Foundation for Natural Gradient and Standard Gradient","created":"2022-02-13","cited_by_count":2,"area":null},{"id":"2408.01517","title":"Gradient flow in parameter space is equivalent to linear interpolation in output space","created":"2024-08-02","cited_by_count":2,"area":null},{"id":"2408.06699","title":"Sparse Variational Student-t Processes for Heavy-tailed Modeling","created":"2024-08-13","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":"2411.06278","title":"A Natural Primal-Dual Hybrid Gradient Method for Adversarial Neural Network Training on Solving Partial Differential Equations","created":"2024-11-09","cited_by_count":2,"area":null},{"id":"2503.16187","title":"Manifold learning in metric spaces","created":"2025-03-20","cited_by_count":2,"area":null},{"id":"2606.21585","title":"A Transport-Based Geometry of Belief-Cost","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.22004","title":"Energy Manifold Natural Gradient Descent: Riemannian Optimization for Neural PDE Solvers","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2610.05071","title":"Discrete Action Matching: Learning Stochastic Dynamics from Samples via State Graphs","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}