Formal Limitations on the Measurement of Mutual Information

Abstract

Measuring mutual information from finite data is difficult. Recent work has considered variational methods maximizing a lower bound. In this paper, we prove that serious statistical limitations are inherent to any method of measuring mutual information. More specifically, we show that any distribution-free high-confidence lower bound on mutual information estimated from N samples cannot be larger than O(ln N).

Cite

Text

McAllester and Stratos. "Formal Limitations on the Measurement of Mutual Information." Artificial Intelligence and Statistics, 2020.

Markdown

[McAllester and Stratos. "Formal Limitations on the Measurement of Mutual Information." Artificial Intelligence and Statistics, 2020.](https://mlanthology.org/aistats/2020/mcallester2020aistats-formal/)

BibTeX

@inproceedings{mcallester2020aistats-formal,
  title     = {{Formal Limitations on the Measurement of Mutual Information}},
  author    = {McAllester, David and Stratos, Karl},
  booktitle = {Artificial Intelligence and Statistics},
  year      = {2020},
  pages     = {875-884},
  volume    = {108},
  url       = {https://mlanthology.org/aistats/2020/mcallester2020aistats-formal/}
}