论文标题
随机马尔可夫梯度下降和训练低位神经网络
Stochastic Markov Gradient Descent and Training Low-Bit Neural Networks
论文作者
论文摘要
现代神经网络的巨大规模激发了人们对神经网络量化的近期兴趣。我们引入了随机马尔可夫梯度下降（SMGD），这是一种适用于训练量化神经网络的离散优化方法。 SMGD算法设计用于在训练过程中高度限制内存的设置。我们提供算法性能的理论保证以及鼓励数值结果。
The massive size of modern neural networks has motivated substantial recent interest in neural network quantization. We introduce Stochastic Markov Gradient Descent (SMGD), a discrete optimization method applicable to training quantized neural networks. The SMGD algorithm is designed for settings where memory is highly constrained during training. We provide theoretical guarantees of algorithm performance as well as encouraging numerical results.
