Low-bit Quantization of Recurrent Neural Network Language Models Using Alternating Direction Methods of Multipliers

2021/11/29 by Junhao Xu, Xie Chen, Xu, Junhao +9
Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Speech Recognition and Synthesis #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2111.14836

openalex publication_date 2021/11/29 · openalex created_date 2021/12/06 · openalex updated_date 2026/07/28

Abstract

The high memory consumption and computational costs of Recurrent neural network language models (RNNLMs) limit their wider application on resource constrained devices. In recent years, neural network quantization techniques that are capable of producing extremely low-bit compression, for example, binarized RNNLMs, are gaining increasing research interests. Directly training of quantized neural networks is difficult. By formulating quantized RNNLMs training as an optimization problem, this paper presents a novel method to train quantized RNNLMs from scratch using alternating direction methods of multipliers (ADMM). This method can also flexibly adjust the trade-off between the compression rate and model performance using tied low-bit quantization tables. Experiments on two tasks: Penn Treebank (PTB), and Switchboard (SWBD) suggest the proposed ADMM quantization achieved a model size compression factor of up to 31 times over the full precision baseline RNNLMs. Faster convergence of 5 times in model training over the baseline binarized RNNLM quantization was also obtained. Index Terms: Language models, Recurrent neural networks, Quantization, Alternating direction methods of multipliers.

Citations

• Training Binary Multilayer Neural Networks for Image Classification using Expectation Backpropagation
• Compressing Deep Convolutional Networks using Vector Quantization
• Distilling the Knowledge in a Neural Network
• Training deep neural networks with low precision multiplications
• Ternary Weight Networks
• Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
• Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMM

Related

• Alternating Multi-bit Quantization for Recurrent Neural Networks
• Training Integer-Only Deep Recurrent Neural Networks
• On the quantization of recurrent neural networks
• Low Precision RNNs: Quantizing RNNs Without Losing Accuracy
• Low-bit Model Quantization for Deep Neural Networks: A Survey