Ternary Singular Value Decomposition as a Better Parameterized Form in Linear Mapping

15 Aug 2023  ·  BoYu Chen, Hanxuan Chen, Jiao He, Fengyu Sun, Shangling Jui ·

We present a simple yet novel parameterized form of linear mapping to achieves remarkable network compression performance: a pseudo SVD called Ternary SVD (TSVD). Unlike vanilla SVD, TSVD limits the $U$ and $V$ matrices in SVD to ternary matrices form in $\{\pm 1, 0\}$. This means that instead of using the expensive multiplication instructions, TSVD only requires addition instructions when computing $U(\cdot)$ and $V(\cdot)$. We provide direct and training transition algorithms for TSVD like Post Training Quantization and Quantization Aware Training respectively. Additionally, we analyze the convergence of the direct transition algorithms in theory. In experiments, we demonstrate that TSVD can achieve state-of-the-art network compression performance in various types of networks and tasks, including current baseline models such as ConvNext, Swim, BERT, and large language model like OPT.

PDF Abstract

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.