The Impact of Anisotropic Covariance Structure on the Training Dynamics and Generalization Error of Linear Networks
stat.ML, cs.LG
Submitted: 2026-01-11
Updated: 2026-10-26
Terminology
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
- Scalable Posterior Uncertainty for Flexible Density-Based Clustering
- A Transport Geometry of Benign Overfitting
- Efficient quadratic entropy with distance sketches