SNT: Sharpness-Minimizing Network Transformation for Fast Compression-friendly Pretraining

05/08/2023
by   Jung Hwan Heo, et al.
0

Model compression has become the de-facto approach for optimizing the efficiency of vision models. Recently, the focus of most compression efforts has shifted to post-training scenarios due to the very high cost of large-scale pretraining. This has created the need to build compressible models from scratch, which can effectively be compressed after training. In this work, we present a sharpness-minimizing network transformation (SNT) method applied during pretraining that can create models with desirable compressibility and generalizability features. We compare our approach to a well-known sharpness-minimizing optimizer to validate its efficacy in creating a flat loss landscape. To the best of our knowledge, SNT is the first pretraining method that uses an architectural transformation to generate compression-friendly networks. We find that SNT generalizes across different compression tasks and network backbones, delivering consistent improvements over the ADAM baseline with up to 2 improvement on quantization. Code to reproduce our results will be made publicly available.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset