A Differentiable Framework for End-to-End Learning of Hybrid Structured Compression ...
Filter pruning and low-rank decomposition are two of the foundational techniques for structured compression. Although recent efforts have explored hybrid approaches aiming to integrate the advantages of both techniques, their performance gains have been modest at best. In this study, we develop a \t...
| Main Authors: | , , |
|---|---|
| Format: | Article in Journal/Newspaper |
| Language: | unknown |
| Published: |
arXiv
2023
|
| Subjects: | |
| Online Access: | https://dx.doi.org/10.48550/arxiv.2309.13077 https://arxiv.org/abs/2309.13077 |
| Summary: | Filter pruning and low-rank decomposition are two of the foundational techniques for structured compression. Although recent efforts have explored hybrid approaches aiming to integrate the advantages of both techniques, their performance gains have been modest at best. In this study, we develop a \textit{Differentiable Framework~(DF)} that can express filter selection, rank selection, and budget constraint into a single analytical formulation. Within the framework, we introduce DML-S for filter selection, integrating scheduling into existing mask learning techniques. Additionally, we present DTL-S for rank selection, utilizing a singular value thresholding operator. The framework with DML-S and DTL-S offers a hybrid structured compression methodology that facilitates end-to-end learning through gradient-base optimization. Experimental results demonstrate the efficacy of DF, surpassing state-of-the-art structured compression methods. Our work establishes a robust and versatile avenue for advancing structured ... : 11 pages, 5 figures, 6 tables ... |
|---|