no code implementations • 26 Nov 2021 • Anbang Wu, Gushu Li, yuke wang, Boyuan Feng, Yufei Ding, Yuan Xie
In this paper, we propose a novel training scheme to mitigate such noise-induced gradient vanishing.
no code implementations • 25 Nov 2021 • Anbang Wu, Gushu Li, Yufei Ding, Yuan Xie
In this paper, we propose a novel training scheme to mitigate such noise-induced gradient vanishing.
no code implementations • 6 Nov 2019 • Anbang Wu, Shuangxi Chen, Chunming Wu
The reparameterization trick has become one of the most useful tools in the field of variational inference.