neural-tangent-kernel topic

{KFAC,EKFAC,Diagonal,Implicit} Fisher Matrices and finite width NTKs in PyTorch

tfjgeorge

codebase for "A Theory of the Inductive Bias and Generalization of Kernel Regression and Wide Neural Networks"

james-simon

A curated list of papers of interesting empirical study and insight on deep learning. Continually updating...

MinghuiChen43

Multi-framework implementation of Deep Kernel Shaping and Tailored Activation Transformations, which are methods that modify neural network models (and their initializations) to make them easier to tr...

google-deepmind

We propose a lossless compression algorithm based on the NTK matrix for DNN. The compressed network yields asymptotically the same NTK as the original (dense and unquantized) network, with its weight...

Model-Compression

Neural Tangent Kernel (NTK) module for the scikit-learn library

392781

Study of the paper 'Neural Thompson Sampling' published in October 2020

RonyAbecidan

A fast, effective data attribution method for neural networks in PyTorch

MadryLab