3 papers
cs.LG2024
Progressive Feedforward Collapse of ResNet Training
Sicong Wang, Kuo Gai, Shihua Zhang
Neural collapse (NC) is a simple and symmetric phenomenon for deep neural networks (DNNs) at the terminal phase of training, where the last-layer features collapse to their class m…
stat.ML2020
Tessellated Wasserstein Auto-Encoders
Kuo Gai, Shihua Zhang
Non-adversarial generative models such as variational auto-encoder (VAE), Wasserstein auto-encoders with maximum mean discrepancy (WAE-MMD), sliced-Wasserstein auto-encoder (SWAE)…
cs.LG2019
Matrix Normal PCA for Interpretable Dimension Reduction and Graphical Noise Modeling
Chihao Zhang, Kuo Gai, Shihua Zhang
Principal component analysis (PCA) is one of the most widely used dimension reduction and multivariate statistical techniques. From a probabilistic perspective, PCA seeks a low-dim…