文章地址: https://arxiv.org/pdf/1707.01209.pdf
Part I: general framework.
We give a general formulation of model compression as constrained optimization.
Related work.
Four categories of model compression.
- Direct learning: min Θ L ( h ( x ; Θ ) ) \min_\Theta L(h(x; \Theta)) minΘL(h(x;Θ)): find the small model with the best loss regardless of the reference.
- Direct compression (DC): min Θ ∥ w − ∆ ( Θ ) ∥ 2 \min_\Theta ∥w − ∆(\Theta)∥^2 </