A Scaling Transition Method from SGDM to SGD with 2ExpLR Strategy

Abstract

In deep learning, the vanilla stochastic gradient descent (SGD) and SGD with heavy-ball momentum (SGDM) methods have a wide range of applications due to their simplicity and great generalization. This paper uses an exponential scaling method to realize a smooth and stable transition from SGDM to SGD, which combines the advantages of the fast training speed of SGDM and the accurate convergence of SGD (named TSGD). We also provide some theoretical results on the convergence of this algorithm. At the same time, we take advantage of the learning rate warmup strategy’s stability and the learning rate decay strategy’s high accuracy. A warmup–decay learning rate strategy with double exponential functions is proposed (named 2ExpLR). The experimental results on different datasets for the proposed algorithms indicate that the accuracy is improved significantly and that the training is faster and more stable.

Keywords

• gradient descent
• scaling transition
• artificial neural network
• image classification