On the Neural Tangent Kernel Analysis of Randomly Pruned Neural Networks

Understand

Motivated by both theory and practice, we study how random pruning of the weights affects a neural network's neural tangent kernel (NTK).

• In particular, this work establishes an equivalence of the NTKs between a fully-connected neural network and its randomly pruned version.
• The equivalence is established under two cases.
• The first main result studies the infinite-width asymptotic.