papers AI Learner
The Github is limit! Click to go to the new site.

On the convergence proof of AMSGrad and a new version

2019-04-07
Tran Thi Phuong, Le Trieu Phong

Abstract

The adaptive moment estimation algorithm Adam (Kingma and Ba, ICLR 2015) is a popular optimizer in the training of deep neural networks. However, Reddi et al. (ICLR 2018) have recently shown that the convergence proof of Adam is problematic and proposed a variant of Adam called AMSGrad as a fix. In this paper, we show that the convergence proof of AMSGrad is also problematic, and we present various fixes for it, which include a new version of AMSGrad.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1904.03590

PDF

http://arxiv.org/pdf/1904.03590


Similar Posts

Comments