Chaobing Song

Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction

2020 · arXiv (Cornell University)

To learn intrinsic low-dimensional structures from high-dimensional data that most discriminate between classes, we propose the principle of Maximal Coding Rate Reduction ($\text{MCR}^2$), an information-theoretic measure that maximizes the coding rate difference between the whole …