55 citations · 63 across the 6 of their papers we have counts for
6 papers
Big Learning
Yulai Cong, Miaoyun Zhao
Recent advances in big/foundation models reveal a promising path for deep learning, where the roadmap steadily moves from big data to big models to (the newly-introduced) big learn…
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…
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…
GO Gradient for Expectation-Based Objectives
Yulai Cong, Miaoyun Zhao, Ke Bai +1
Within many machine learning algorithms, a fundamental problem concerns efficient calculation of an unbiased gradient wrt parameters $\gammav$ for expectation-based objectives $\Eb…