We propose a novel technique for faster Neural Network (NN) training by systematically approximating all the constituent matrix multiplications and convolutions. This approach is complementary to other approximation techniques, requires no changes to the dimensions of the network layers, hence compatible with existing training frameworks. We first analyze the applicability of the existing methods for approximating matrix multiplication to NN training, and extend the most suitable column-row sampling algorithm to approximating multi-channel convolutions. We apply approximate tensor operations to training MLP, CNN and LSTM network architectures on MNIST, CIFAR-100 and Penn Tree Bank datasets and demonstrate 30%-80% reduction in the amount of computations while maintaining little or no impact on the test accuracy. Our promising results encourage further study of general methods for approximating tensor operations and their application to NN training.

通过对张量运算（矩阵乘法和卷积）应用基于样本的近似，提出了一种用于深度神经网络加速训练的新技术。应用到 MLP 和 CNN 网络的 MNIST，CIFAR-10 和 ImageNet 数据集的训练实验结果表明，该方法可以大幅度减少计算量和通讯量，并以不会对最终测试准确率产生可感知影响的方式提升训练速度。

使用近似张量运算加速神经网络训练