SinReQ: Generalized Sinusoidal Regularization for Low-Bitwidth Deep Quantized Training
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.
Code (0)
등록된 구현이 없습니다.
Tasks
QuantizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
WAVEQ: GRADIENT-BASED DEEP QUANTIZATION OF NEURAL NETWORKS THROUGH SINUSOIDAL REGULARIZATION
Deep quantization of neural networks below eight bits can lead to superlinear benefits in storage and compute efficiency. However, homogeneously quantizing all the layers to the same level does not account for the distin…
QuantizationWaveQ: Gradient-Based Deep Quantization of Neural Networks through Sinusoidal Adaptive Regularization
As deep neural networks make their ways into different domains, their compute efficiency is becoming a first-order constraint. Deep quantization, which reduces the bitwidth of the operations (below 8 bits), offers a uniq…
QuantizationMixed-Precision Quantized Neural Network with Progressively Decreasing Bitwidth For Image Classification and Object Detection
Efficient model inference is an important and practical issue in the deployment of deep neural network on resource constraint platforms. Network quantization addresses this problem effectively by leveraging low-bit repre…
General Classificationimage-classificationImage Classificationobject-detection+2FAMES: Fast Approximate Multiplier Substitution for Mixed-Precision Quantized DNNs--Down to 2 Bits!
A widely-used technique in designing energy-efficient deep neural network (DNN) accelerators is quantization. Recent progress in this direction has reduced the bitwidths used in DNN down to 2. Meanwhile, many prior works…
QuantizationHiKonv: High Throughput Quantized Convolution With Novel Bit-wise Management and Computation
Quantization for Convolutional Neural Network (CNN) has shown significant progress with the intention of reducing the cost of computation and storage with low-bitwidth data inputs. There are, however, no systematic studi…
CPUManagementQuantization