EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis

arXiv: Learning, 2019.

Cited by: 8|Views76
EI

Abstract:

Reducing the test time resource requirements of a neural network while preserving test accuracy is crucial for running inference on resource-constrained devices. To achieve this goal, we introduce a novel network reparameterization based on the Kronecker-factored eigenbasis (KFE), and then apply Hessian-based structured pruning methods ...More

Code:

Data:

Your rating :
0

 

Tags
Comments