On the linearity of large non-linear models: when and why the tangent kernel is constant.

Chaoyue Liu Libin Zhu Mikhail Belkin

Published in: NeurIPS (2020)

Keyphrases

kernel methods
multiscale
parameter estimation
computational models
machine learning
genetic algorithm
prior knowledge
markov random field
model selection
linear combination
complex systems
statistical models
neural network model
mathematical models