{"total":46,"rows":[{"id":"2107.04562","title":"The Bayesian Learning Rule","created":"2021-07-09","cited_by_count":99,"area":null},{"id":"2105.01424","title":"On the Linear convergence of Natural Policy Gradient Algorithm","created":"2021-05-04","cited_by_count":48,"area":null},{"id":"2101.10506","title":"Finite Sample Analysis of Two-Time-Scale Natural Actor-Critic Algorithm","created":"2021-01-26","cited_by_count":39,"area":null},{"id":"2110.02719","title":"The Information Geometry of Unsupervised Reinforcement Learning","created":"2021-10-06","cited_by_count":37,"area":null},{"id":"2310.02951","title":"A Fisher-Rao gradient flow for entropy-regularised Markov decision processes in Polish spaces","created":"2023-10-04","cited_by_count":23,"area":null},{"id":"2106.12506","title":"Sampling with Mirrored Stein Operators","created":"2021-06-23","cited_by_count":17,"area":null},{"id":"2209.15382","title":"Linear Convergence for Natural Policy Gradient with Log-linear Policy Parametrization","created":"2022-09-30","cited_by_count":17,"area":null},{"id":"2202.12275","title":"Partitioned Variational Inference: A Framework for Probabilistic Federated Learning","created":"2022-02-24","cited_by_count":13,"area":null},{"id":"2405.20250","title":"Entropy annealing for policy mirror descent in continuous time and space","created":"2024-05-30","cited_by_count":12,"area":null},{"id":"2405.12888","title":"Keep the Momentum: Conservation Laws beyond Euclidean Gradient Flows","created":"2024-05-21","cited_by_count":11,"area":null},{"id":"2406.04012","title":"Theoretical Guarantees for Variational Inference with Fixed-Variance Mixture of Gaussians","created":"2024-06-06","cited_by_count":11,"area":null},{"id":"2409.01464","title":"Stein transport for Bayesian inference","created":"2024-09-02","cited_by_count":11,"area":null},{"id":"2206.02041","title":"First-Order Algorithms for Min-Max Optimization in Geodesic Metric Spaces","created":"2022-06-04","cited_by_count":10,"area":null},{"id":"2311.02374","title":"Riemannian stochastic optimization methods avoid strict saddle points","created":"2023-11-04","cited_by_count":8,"area":null},{"id":"2406.01870","title":"Understanding Stochastic Natural Gradient Variational Inference","created":"2024-06-04","cited_by_count":8,"area":null},{"id":"2109.04442","title":"FGOT: Graph Distances based on Filters and Optimal Transport","created":"2021-09-09","cited_by_count":7,"area":null},{"id":"2506.13613","title":"Variational Inference with Mixtures of Isotropic Gaussians","created":"2025-06-16","cited_by_count":6,"area":null},{"id":"2205.07017","title":"Importance Weighted Structure Learning for Scene Graph Generation","created":"2022-05-14","cited_by_count":4,"area":null},{"id":"2302.03390","title":"Learning Discretized Neural Networks under Ricci Flow","created":"2023-02-07","cited_by_count":4,"area":null},{"id":"2406.19195","title":"Estimating Long-term Heterogeneous Dose-response Curve: Generalization Bound Leveraging Optimal Transport Weights","created":"2024-06-27","cited_by_count":4,"area":null},{"id":"2110.02398","title":"Approximate Newton policy gradient algorithms","created":"2021-10-05","cited_by_count":3,"area":null},{"id":"2201.11697","title":"Constrained Structure Learning for Scene Graph Generation","created":"2022-01-27","cited_by_count":3,"area":null},{"id":"2206.04663","title":"Provably efficient variational generative modeling of quantum many-body systems via quantum-probabilistic information geometry","created":"2022-06-09","cited_by_count":3,"area":null},{"id":"2206.10860","title":"Bregman Power k-Means for Clustering Exponential Family Data","created":"2022-06-22","cited_by_count":3,"area":null},{"id":"2503.08748","title":"Mirror Descent and Novel Exponentiated Gradient Algorithms Using Trace-Form Entropies and Deformed Logarithms","created":"2025-03-11","cited_by_count":3,"area":null},{"id":"2506.13150","title":"Federated ADMM from Bayesian Duality","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2510.19163","title":"Natural Gradient VI: Guarantees for Non-Conjugate Models","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2211.15880","title":"Mirror descent of Hopfield model","created":"2022-11-29","cited_by_count":2,"area":null},{"id":"2504.02618","title":"Variational Online Mirror Descent for Robust Learning in Schr\\\"odinger Bridge","created":"2025-04-03","cited_by_count":2,"area":null},{"id":"2111.08002","title":"Natural Gradient Variational Inference with Gaussian Mixture Models","created":"2021-11-15","cited_by_count":1,"area":null},{"id":"2207.11382","title":"Density-Aware Personalized Training for Risk Prediction in Imbalanced Medical Data","created":"2022-07-23","cited_by_count":1,"area":null},{"id":"2310.03884","title":"Information Geometry for the Working Information Theorist","created":"2023-10-05","cited_by_count":1,"area":null},{"id":"2405.01507","title":"Accelerating Convergence in Bayesian Few-Shot Classification","created":"2024-05-02","cited_by_count":1,"area":null},{"id":"2604.00683","title":"Convergence of projected stochastic natural gradient variational inference for various step size and sample or batch size schedules","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2208.13898","title":"Conjugate Natural Selection","created":"2022-08-29","cited_by_count":0,"area":null},{"id":"2210.15323","title":"Stochastic Mirror Descent in Average Ensemble Models","created":"2022-10-27","cited_by_count":0,"area":null},{"id":"2306.10587","title":"Acceleration in Policy Optimization","created":"2023-06-18","cited_by_count":0,"area":null},{"id":"2505.10272","title":"Spike-timing-dependent Hebbian learning as noisy gradient descent","created":"2025-05-15","cited_by_count":0,"area":null},{"id":"2512.09358","title":"Minimization of Functions on Dually Flat Spaces Using Geodesic Descent Based on Dual Connections","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2603.12838","title":"A New Kernel Regularity Condition for Distributed Mirror Descent: Broader Coverage and Simpler Analysis","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2603.17527","title":"Mirror Descent on Riemannian Manifolds","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2604.24047","title":"Generalising maximum mean discrepancy: kernelised functional Bregman divergences","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2606.13984","title":"A Bregman Perspective on Classification and Regression Trees","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2608.30778","title":"Reciprocity Separates Gradient Flow from Rotation in Conservative Physical Learning","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.12991","title":"Information-Induced Training Geometry: Exact Reduction, Canonical Completion, and Structured Expressivity","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2609.16805","title":"Geometry of learning dynamics: Gradient descent versus natural gradient on the ridge of optimization","created":"2026-09-15","cited_by_count":0,"area":null}],"next_cursor":null}