Paper ID: 2203.01603

AdaFamily: A family of Adam-like adaptive gradient methods

Hannes Fassold

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.

Submitted: Mar 3, 2022