How Inefficient Is Natural Gradient Descent? From Exact Optimality to (sqrt d) Divergence
stat.ML, cs.LG
Submitted: 2026-10-05
Updated: 2026-10-05
Sources
- Dynamical Systems induced by Canonical Divergence in dually flat manifolds
- Minimization of Functions on Dually Flat Spaces Using Geodesic Descent Based on Dual Connections
- Fisher-Rao distance on the covariance cone
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- Efficient quadratic entropy with distance sketches
- Embedding-Bias in Conditional Independence Testing
- From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier