Data-dependent coresets for compressing neural networks with applications to generalization bounds
We present an efficient coresets-based neural network compression algorithm that sparsifies the parameters of a trained fully-connected neural network in a manner that provably approximates the network's output. Our approach is based on an importance sampling scheme that judiciously defines a s...
Format: | Article |
---|---|
Language: | English |
Published: |
2021-11-03T14:15:59Z.
|
Subjects: | |
Online Access: | Get fulltext |