Formal Limitations on the Measurement of Mutual Information

Autor:	McAllester, David, Stratos, Karl
Rok vydání:	2018
Předmět:	Computer Science - Information Theory Computer Science - Machine Learning Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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 ).
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1811.04251 Zobrazit plný text záznamu View this record from Arxiv