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

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.

8 pages, 8 figures, 2 tables

References in corpus (9)

• Distilling the Knowledge in a Neural Network
• AMC: AutoML for Model Compression and Acceleration on Mobile Devices
• Rethinking the Value of Network Pruning
• A Survey of Model Compression and Acceleration for Deep Neural Networks
• Speeding up Convolutional Neural Networks with Low Rank Expansions
• Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers
• Compression-aware Training of Deep Networks
• Trained Rank Pruning for Efficient Deep Neural Networks
• Generating Natural Language Adversarial Examples through An Improved Beam Search Algorithm