VecQ: Minimal Loss DNN Model Compression With Vectorized Weight Quantization

Quantization-based language model compression

This paper describes two techniques for reducing the size of statistical back-off -gram language models in computer memory. Language model compression is achieved through a combination of quantizing language model probabilities and back-off weights and the pruning of parameters that are determined to be unnecessary after quantization. The recognition performance of the original and compressed l...

Loss-aware Weight Quantization of Deep Networks

The huge size of deep networks hinders their use in small computing devices. In this paper, we consider compressing the network by weight quantization. We extend a recently proposed loss-aware weight binarization scheme to ternarization, with possibly different scaling parameters for the positive and negative weights, and m-bit (where m > 2) quantization. Experiments on feedforward and recurren...

Model compression via distillation and quantization

Deep neural networks (DNNs) continue to make significant advances, solving tasks from image classification to translation or reinforcement learning. One aspect of the field receiving considerable attention is efficiently executing deep models in resource-constrained environments, such as mobile or embedded devices. This paper focuses on this problem, and proposes two new compression methods, wh...

Vector Quantization for Image Compression-Concept Quantization

Medical Image Compression Using Vector Quantization and Gaussian Mixture Model

Codebook design for vector quantization could be performed using clustering technique. The Gaussian Mixture Modeling (GMM) clustering algorithm involves modeling a statistical distribution by a mixture (or weighted sum) of other distributions. GMM has proven superior efficiency in both time and accuracy and has been used with vector quantization in some applications. This paper introduces a med...