A Differentiable Framework for End-to-End Learning of Hybrid Structured Compression
This work addresses the need for more effective compression techniques in machine learning, though it appears incremental as it builds on existing methods like mask learning and singular value thresholding.
The paper tackles the problem of hybrid structured compression by developing a differentiable framework that integrates filter and rank selection into a single formulation, achieving state-of-the-art performance in experiments.
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 compression techniques.