E2-Train: Training State-of-the-art CNNs with Over 80% Energy Savings
arXiv:1910.13349
Abstract
Convolutional neural networks (CNNs) have been increasingly deployed to edge devices. Hence, many efforts have been made towards efficient CNN inference in resource-constrained platforms. This paper attempts to explore an orthogonal direction: how to conduct more energy-efficient training of CNNs, so as to enable on-device training. We strive to reduce the energy cost during training, by dropping unnecessary computations from three complementary levels: stochastic mini-batch dropping on the data level; selective layer update on the model level; and sign prediction for low-cost, low-precision back-propagation, on the algorithm level. Extensive simulations and ablation studies, with real energy measurements from an FPGA board, confirm the superiority of our proposed strategies and demonstrate remarkable energy savings for training. For example, when training ResNet-74 on CIFAR-10, we achieve aggressive energy savings of >90% and >60%, while incurring a top-1 accuracy loss of only about 2% and 1.2%, respectively. When training ResNet-110 on CIFAR-100, an over 84% training energy saving is achieved without degrading inference accuracy.
References in corpus (5)
- On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima
- Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutes
- Training Deep Neural Networks with 8-bit Floating Point Numbers
- Highway and Residual Networks learn Unrolled Iterative Estimation
- AdaScale: Towards Real-time Video Object Detection Using Adaptive Scaling