SiPPing Neural Networks: Sensitivity-informed Provable Pruning of Neural Networks

Cited by: 0|Views17

Abstract:

We introduce a pruning algorithm that provably sparsifies the parameters of a trained model in a way that approximately preserves the model's predictive accuracy. Our algorithm uses a small batch of input points to construct a data-informed importance sampling distribution over the network's parameters, and adaptively mixes a sampling-b...More

Code:

Data:

Full Text
Bibtex
Your rating :
0

 

Tags
Comments