QReg: On Regularization Effects of Quantization
This addresses the problem of improving model generalization in vision tasks through quantization, offering an incremental insight into its regularization effects.
The paper investigates weight quantization in deep neural networks as a form of regularization, showing that the regularization effect correlates with quantization precision, and proposes 8-bit quantization as a reliable regularization method for vision tasks.
In this paper we study the effects of quantization in DNN training. We hypothesize that weight quantization is a form of regularization and the amount of regularization is correlated with the quantization level (precision). We confirm our hypothesis by providing analytical study and empirical results. By modeling weight quantization as a form of additive noise to weights, we explore how this noise propagates through the network at training time. We then show that the magnitude of this noise is correlated with the level of quantization. To confirm our analytical study, we performed an extensive list of experiments summarized in this paper in which we show that the regularization effects of quantization can be seen in various vision tasks and models, over various datasets. Based on our study, we propose that 8-bit quantization provides a reliable form of regularization in different vision tasks and models.