SinReQ: Generalized Sinusoidal Regularization for Low-Bitwidth Deep Quantized Training

Abstract

Deep quantization of neural networks (below eight bits) offers significant promise in reducing their compute and storage cost. Albeit alluring, without special techniques for training and optimization, deep quantization results in significant accuracy loss. To further mitigate this loss, we propose a novel sinusoidal regularization, called SinReQ1, for deep quantized training. SinReQ adds a periodic term to the original objective function of the underlying training algorithm. SinReQ exploits the periodicity, differentiability, and the desired convexity profile in sinusoidal functions to automatically propel weights towards values that are inherently closer to quantization levels. Since, this technique does not require invasive changes to the training procedure, SinReQ can harmoniously enhance quantized training algorithms. SinReQ offers generality and flexibility as it is not limited to a certain bitwidth or a uniform assignment of bitwidths across layers. We carry out experimentation using the AlexNet, CIFAR-10, ResNet-18, ResNet-20, SVHN, and VGG-11 DNNs with three to five bits for quantization and show the versatility of SinReQ in enhancing multiple quantized training algorithms, DoReFa [32] and WRPN [24]. Averaging across all the bit configurations shows that SinReQ closes the accuracy gap between these two techniques and the full-precision runs by 32.4% and 27.5%, respectively. That is improving the absolute accuracy of DoReFa and WRPN by 2.8% and 2.1%, respectively.

References in corpus (12)

• DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
• Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
• Binarized Neural Networks
• Ternary Weight Networks
• Trained Ternary Quantization
• The Loss Surfaces of Multilayer Networks
• PACT: Parameterized Clipping Activation for Quantized Neural Networks
• WRPN: Wide Reduced-Precision Networks
• Loss-aware Binarization of Deep Networks
• Loss-aware Weight Quantization of Deep Networks
• ReLeQ: A Reinforcement Learning Approach for Deep Quantization of Neural Networks
• On Periodic Functions as Regularizers for Quantization of Neural Networks

Cited by in corpus (4)

• Neural Network Distiller: A Python Package For DNN Compression Research
• ReLeQ: A Reinforcement Learning Approach for Deep Quantization of Neural Networks
• Robust Quantization: One Model to Rule Them All
• WaveQ: Gradient-Based Deep Quantization of Neural Networks through Sinusoidal Adaptive Regularization