55 citations · 124 across the 12 of their papers we have counts for
5 papers · 1 filter
Bridging Maximum Likelihood and Adversarial Learning via -Divergence
Miaoyun Zhao, Yulai Cong, Shuyang Dai +1
Maximum likelihood (ML) and adversarial learning are two popular approaches for training generative models, and from many perspectives these techniques are complementary. ML learni…
GO Hessian for Expectation-Based Objectives
Yulai Cong, Miaoyun Zhao, Jianqiao Li +2
An unbiased low-variance gradient estimator, termed GO gradient, was proposed recently for expectation-based objectives $\mathbb{E}_{q_{\boldsymbolγ}(\boldsymbol{y})} [f(\boldsymbo…
Deep Autoencoding Topic Model with Scalable Hybrid Bayesian Inference
Hao Zhang, Bo Chen, Yulai Cong +3
To build a flexible and interpretable model for document analysis, we develop deep autoencoding topic model (DATM) that uses a hierarchy of gamma distributions to construct its mul…
GAN Memory with No Forgetting
Yulai Cong, Miaoyun Zhao, Jianqiao Li +2
As a fundamental issue in lifelong learning, catastrophic forgetting is directly caused by inaccessible historical data; accordingly, if the data (information) were memorized perfe…
On Leveraging Pretrained GANs for Generation with Limited Data
Miaoyun Zhao, Yulai Cong, Lawrence Carin
Recent work has shown generative adversarial networks (GANs) can generate highly realistic images, that are often indistinguishable (by humans) from real images. Most images so gen…