Bounds for the smallest eigenvalue of the NTK for arbitrary spherical data of arbitrary dimension, Michael Murray 1 Department of Mathematics, UCLA

Neural Information Processing Systems 

Bounds on the smallest eigenvalue of the neural tangent kernel (NTK) are a key ingredient in the analysis of neural network optimization and memorization.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found