R Jie, J Gao, A Vasnev, MN Tran - arXiv preprint arXiv:2008.07277, 2020 - academia.edu
In this study, we investigate learning rate adaption at different levels based on the hyper- gradient descent framework and propose a method that adaptively learns the optimizer …
In machine learning, we are concerned with developing algorithms that are able to learn, that is, to accumulate knowledge about how to do a task without having been programmed …