ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization

Cong Guo 0003, Chen Zhang 0001, Jingwen Leng, Zihan Liu, Fan Yang 0024, Yunxin Liu, Minyi Guo, Yuhao Zhu 0001. ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization. In 55th IEEE/ACM International Symposium on Microarchitecture, MICRO 2022, Chicago, IL, USA, October 1-5, 2022. pages 1414-1433, IEEE, 2022. [doi]

Abstract

Abstract is missing.