2 papers
cs.LG2021
Adversarial Information Bottleneck
Penglong Zhai, Shihua Zhang
The information bottleneck (IB) principle has been adopted to explain deep learning in terms of information compression and prediction, which are balanced by a trade-off hyperparam…
cs.LG2020
Learnable Graph-regularization for Matrix Decomposition
Penglong Zhai, Shihua Zhang
Low-rank approximation models of data matrices have become important machine learning and data mining tools in many fields including computer vision, text mining, bioinformatics an…