Skip to content

Latest commit

 

History

History
7 lines (5 loc) · 322 Bytes

Differentiable-Compression.md

File metadata and controls

7 lines (5 loc) · 322 Bytes

Differentiable Compression

This summary records compression methods that get rid of the non-differentiable compression operation in training.

  • Relaxed Quantization for Discretized Neural Networks
  • Learning sparse neural networks through L0 regularization
  • ProxQuant: Quantized Neural Networks via Proximal Operators