Paper Info
Title
SDQ: Stochastic Differentiable Quantization with Mixed Precision.
Abstract
In order to deploy deep models in a computationally efficient manner, model quantization approaches have been frequently used. In addition, as new hardware that supports various-bit arithmetic operations, recent research on mixed precision quantization (MPQ) begins to fully leverage the capacity of representation by searching various bitwidths for different layers and modules in a network. However, previous studies mainly search the MPQ strategy in a costly scheme using reinforcement learning, neural architecture search, etc., or simply utilize partial prior knowledge for bitwidth distribution, which might be biased and sub-optimal. In this work, we present a novel Stochastic Differentiable Quantization (SDQ) method that can automatically learn the MPQ strategy in a more flexible and globally-optimized space with a smoother gradient approximation. Particularly, Differentiable Bitwidth Parameters (DBPs) are employed as the probability factors in stochastic quantization between adjacent bitwidth. After the optimal MPQ strategy is acquired, we further train our network with the entropy-aware bin regularization and knowledge distillation. We extensively evaluate our method on different networks, hardwares (GPUs and FPGA), and datasets. SDQ outperforms all other state-of-the-art mixed or single precision quantization with less bitwidth, and are even better than the original full-precision counterparts across various ResNet and MobileNet families, demonstrating the effectiveness and superiority of our method. Code will be publicly available.
Year
Venue
DocType
2022
International Conference on Machine Learning
Conference
Citations 
PageRank 
References 
0
0.34
0
Authors
8
Name
Order
Citations
PageRank
Xijie Huang1192.26
Zhiqiang Shen2639.46
Shichao Li332.08
Zechun Liu4165.27
Xianghong Hu500.34
Jeffry Wicaksana600.34
Bo Xing77332471.43
Kwang-Ting Cheng85755513.90