Quantized Sparse Weight Decomposition for Neural Network Compression

• Published in: arXiv.org
• Main Authors: Kuzmin, Andrey, Mart van Baalen, Nagel, Markus, Behboodi, Arash
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 22.07.2022
• Subjects: Mathematical analysis; Model accuracy; Neural networks; Tensors; Vector quantization

In this paper, we introduce a novel method of neural network weight compression. In our method, we store weight tensors as sparse, quantized matrix factors, whose product is computed on the fly during inference to generate the target model's weights. We use projected gradient descent methods to...