{"total":22,"rows":[{"id":"2107.04562","title":"The Bayesian Learning Rule","created":"2021-07-09","cited_by_count":99,"area":null},{"id":"2402.03496","title":"Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective","created":"2024-02-05","cited_by_count":25,"area":null},{"id":"2209.11533","title":"A Unified Perspective on Natural Gradient Variational Inference with Gaussian Mixture Models","created":"2022-09-23","cited_by_count":22,"area":null},{"id":"2302.07384","title":"The Geometry of Neural Nets' Parameter Spaces Under Reparametrization","created":"2023-02-14","cited_by_count":16,"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":"2302.09738","title":"Simplifying Momentum-based Positive-definite Submanifold Optimization with Applications to Deep Learning","created":"2023-02-20","cited_by_count":10,"area":null},{"id":"2312.05705","title":"Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC","created":"2023-12-09","cited_by_count":9,"area":null},{"id":"2406.01870","title":"Understanding Stochastic Natural Gradient Variational Inference","created":"2024-06-04","cited_by_count":8,"area":null},{"id":"2107.10884","title":"Structured second-order methods via natural gradient descent","created":"2021-07-22","cited_by_count":7,"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":"2111.08792","title":"PredProp: Bidirectional Stochastic Optimization with Precision Weighted Predictive Coding","created":"2021-11-16","cited_by_count":3,"area":null},{"id":"2303.04397","title":"The Lie-Group Bayesian Learning Rule","created":"2023-03-08","cited_by_count":3,"area":null},{"id":"2507.07853","title":"Optimization Guarantees for Square-Root Natural-Gradient Variational Inference","created":"2025-07-10","cited_by_count":3,"area":null},{"id":"2606.23357","title":"SOAP-Bubbles: Structured Weight Uncertainty for Neural Networks","created":"2026-06-22","cited_by_count":3,"area":null},{"id":"2509.15641","title":"Information Geometry of Variational Bayes","created":"2025-09-19","cited_by_count":2,"area":null},{"id":"2112.03734","title":"Towards Modeling and Resolving Singular Parameter Spaces using Stratifolds","created":"2021-12-07","cited_by_count":1,"area":null},{"id":"2304.14251","title":"Variational Bayes Made Easy","created":"2023-04-27","cited_by_count":1,"area":null},{"id":"2206.08598","title":"Characterizing Learning Dynamics under Relative Reparameterization of Singular Models","created":"2022-06-17","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":"2409.15393","title":"Approximated Orthogonal Projection Unit: Stabilizing Regression Network Training Using Natural Gradient","created":"2024-09-23","cited_by_count":0,"area":null},{"id":"2502.06268","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2505.13614","title":"Deterministic Bounds and Random Estimates of Metric Tensors on Neuromanifolds","created":"2025-05-19","cited_by_count":0,"area":null}],"next_cursor":null}