A Highly Effective Low-Rank Compression of Deep Neural Networks with Modified Beam-Search and Modified Stable Rank

TL;DR

This paper introduces BSR, a low-rank compression method for deep neural networks that uses modified beam-search and stable rank techniques, requiring minimal hyperparameter tuning and outperforming previous methods in accuracy and compression.

Contribution

The paper presents a novel low-rank compression approach with automatic rank selection and a single hyperparameter, improving performance over existing methods.

Findings

BSR achieves superior accuracy and compression ratio trade-offs.

BSR performs on par or better than structured pruning methods.

BSR can be combined with quantization for further compression.

Abstract

Compression has emerged as one of the essential deep learning research topics, especially for the edge devices that have limited computation power and storage capacity. Among the main compression techniques, low-rank compression via matrix factorization has been known to have two problems. First, an extensive tuning is required. Second, the resulting compression performance is typically not impressive. In this work, we propose a low-rank compression method that utilizes a modified beam-search for an automatic rank selection and a modified stable rank for a compression-friendly training. The resulting BSR (Beam-search and Stable Rank) algorithm requires only a single hyperparameter to be tuned for the desired compression ratio. The performance of BSR in terms of accuracy and compression ratio trade-off curve turns out to be superior to the previously known low-rank compression methods. Furthermore, BSR can perform on par with or better than the state-of-the-art structured pruning methods. As with pruning, BSR can be easily combined with quantization for an additional compression.