Skip to content

Latest commit

 

History

History
25 lines (17 loc) · 1.32 KB

layer_compensated_pruning.md

File metadata and controls

25 lines (17 loc) · 1.32 KB

(NIPS 2018 talk for ML on device)

May 2019

tl;dr: Layer-wise pruning, but with layer-compensated loss.

Overall impression

Previous method approximates the pruning loss increase with the L1 or L2 of the pruned filter. This is not true. LcP first approximates the layer-wise error compensation and then uses naive pruning (global greedy pruning algorithms) to prune network.

Key ideas

  • Two problems in pruning the network: how many to prune and which to prune. The first is also named layer scheduling.
  • Naive pruning algorithm: global iterative pruning without layer scheduling.
  • Two approximation in prior art of multi-filter pruning:
    • Approximate loss change with a ranking metric (the paper addresses this issue)
    • Approximate the effect of multiple filter pruning with addition of single layer pruning.
  • The paper assumes that the approximation error to be identical for filters in the same layer. Therefore only L latent variables $\beta_l, l=1, ..., L$ need to be approximated.

Technical details

  • Summary of technical details

Notes

  • Questions and notes on how to improve/revise the current work