-
Improving Text Generation with Student-Forcing Optimal Transport
Neural language models are often trained with maximum likelihood estimat...
10/12/2020 ∙ by Guoyin Wang, et al. ∙
2
∙
share
read it
-
GO Hessian for Expectation-Based Objectives
An unbiased low-variance gradient estimator, termed GO gradient, was pro...
06/16/2020 ∙ by Yulai Cong, et al. ∙
0
∙
share
read it
-
GAN Memory with No Forgetting
Seeking to address the fundamental issue of memory in lifelong learning,...
06/13/2020 ∙ by Yulai Cong, et al. ∙
0
∙
share
read it
-
Adversarial Learning of a Sampler Based on an Unnormalized Distribution
We investigate adversarial learning in the case when only an unnormalize...
01/03/2019 ∙ by Chunyuan Li, et al. ∙
14
∙
share
read it
