Derives geodesic ridge regularization and Riemannian Gibbs Process prior for feature-learning wide neural networks, generalizing kernel-regime results via function-space axiomatization.
Smooth manifolds
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
The Lebesgue measure of ε-forging sets decays as O(ε) or ε^d for linear models and as ε^{(d-r)/2} under mild regularity assumptions, with vanishing probability of random sampling.
Scale symmetry reduction applied to singular Lagrangians via De-Donder-Weyl formalism yields equivalent frictional dynamics for particles and fields, with applications to general relativity.
citing papers explorer
-
Canonical Regularisation of Wide Feature-Learning Neural Networks
Derives geodesic ridge regularization and Riemannian Gibbs Process prior for feature-learning wide neural networks, generalizing kernel-regime results via function-space axiomatization.
-
The Measure of Deception: An Analysis of Data Forging in Machine Unlearning
The Lebesgue measure of ε-forging sets decays as O(ε) or ε^d for linear models and as ε^{(d-r)/2} under mild regularity assumptions, with vanishing probability of random sampling.
-
Gauge Symmetries, Contact Reduction, and Singular Field Theories
Scale symmetry reduction applied to singular Lagrangians via De-Donder-Weyl formalism yields equivalent frictional dynamics for particles and fields, with applications to general relativity.