Information-Theoretic Methods in Deep Neural Networks: Recent Advances and Emerging Opportunities

Abstract

We present a review on the recent advances and emerging opportunities around the theme of analyzing deep neural networks (DNNs) with information-theoretic methods. We first discuss popular information-theoretic quantities and their estimators. We then introduce recent developments on information-theoretic learning principles (e.g., loss functions, regularizers and objectives) and their parameterization with DNNs. We finally briefly review current usages of information-theoretic concepts in a few modern machine learning problems and list a few emerging opportunities.

Cite

Text

Yu et al. "Information-Theoretic Methods in Deep Neural Networks: Recent Advances and Emerging Opportunities." International Joint Conference on Artificial Intelligence, 2021. doi:10.24963/IJCAI.2021/633

Markdown

[Yu et al. "Information-Theoretic Methods in Deep Neural Networks: Recent Advances and Emerging Opportunities." International Joint Conference on Artificial Intelligence, 2021.](https://mlanthology.org/ijcai/2021/yu2021ijcai-information/) doi:10.24963/IJCAI.2021/633

BibTeX

@inproceedings{yu2021ijcai-information,
  title     = {{Information-Theoretic Methods in Deep Neural Networks: Recent Advances and Emerging Opportunities}},
  author    = {Yu, Shujian and Giraldo, Luis G. Sánchez and Príncipe, José C.},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2021},
  pages     = {4669-4678},
  doi       = {10.24963/IJCAI.2021/633},
  url       = {https://mlanthology.org/ijcai/2021/yu2021ijcai-information/}
}