#jsDisabledContent { display:none; } My Account | Register | Help

# Sanov's theorem

Article Id: WHEBN0031587409
Reproduction Date:

 Title: Sanov's theorem Author: World Heritage Encyclopedia Language: English Subject: Collection: Publisher: World Heritage Encyclopedia Publication Date:

### Sanov's theorem

In information theory, Sanov's theorem gives a bound on the probability of observing an atypical sequence of samples from a given probability distribution.

Let A be a set of probability distributions over an alphabet X, and let q be an arbitrary distribution over X (where q may or may not be in A). Suppose we draw n i.i.d. samples from q, represented by the vector x^n = x_1, x_2, \ldots, x_n. Further, let us ask that the empirical distribution, \hat{p}_{x^n}, of the samples falls within the set A—formally, we write \{x^n : \hat{p}_{x^n} \in A\}. Then,

q^n(x^n) \le (n+1)^{|X|} 2^{-nD_{\mathrm{KL}}(p^*||q)},

where

In words, the probability of drawing an atypical distribution is proportional to the KL distance from the true distribution to the atypical one; in the case that we consider a set of possible atypical distributions, there is a dominant atypical distribution, given by the information projection.

Furthermore, if A is a closed set,

\lim_{n\to\infty}\frac{1}{n}\log q^n(x^n) = -D_{\mathrm{KL}}(p^*||q).

## References

• Cover, Thomas M.; Thomas, Joy A. (2006). Elements of Information Theory (2 ed.). Hoboken, New Jersey: Wiley Interscience. p. 362.
• Sanov, I. N. (1957) "On the probability of large deviations of random variables". Mat. Sbornik 42, 11–44.

This article was sourced from Creative Commons Attribution-ShareAlike License; additional terms may apply. World Heritage Encyclopedia content is assembled from numerous content providers, Open Access Publishing, and in compliance with The Fair Access to Science and Technology Research Act (FASTR), Wikimedia Foundation, Inc., Public Library of Science, The Encyclopedia of Life, Open Book Publishers (OBP), PubMed, U.S. National Library of Medicine, National Center for Biotechnology Information, U.S. National Library of Medicine, National Institutes of Health (NIH), U.S. Department of Health & Human Services, and USA.gov, which sources content from all federal, state, local, tribal, and territorial government publication portals (.gov, .mil, .edu). Funding for USA.gov and content contributors is made possible from the U.S. Congress, E-Government Act of 2002.

Crowd sourced content that is contributed to World Heritage Encyclopedia is peer reviewed and edited by our editorial staff to ensure quality scholarly research articles.