We propose AdaFamily, a novel method for training deep neural networks. It is a family of adaptive gradient methods and can be interpreted as sort of a blend of the optimization algorithms Adam, AdaBelief and AdaMomentum. We perform experiments on standard datasets for image classification, demonstrating that our proposed method outperforms these algorithms.

翻译：我们提出“AdaFamily ” ( AdaFamily ), 这是一种培训深层神经网络的新颖方法。这是一个适应性梯度方法的组合,可以被解读为优化算法的组合。 我们用标准数据集进行图像分类实验,证明我们建议的方法优于这些算法。 我们建议的方法是“AdaBelief ” ( AdaBelief)和“AdaMomentum ” ( AdaMomentum ) 。