Sanov's theorem

Last updated

In mathematics and information theory, Sanov's theorem gives a bound on the probability of observing an atypical sequence of samples from a given probability distribution. In the language of large deviations theory, Sanov's theorem identifies the rate function for large deviations of the empirical measure of a sequence of i.i.d. random variables.

Contents

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 . Then, we have the following bound on the probability that the empirical measure of the samples falls within the set A:

,

where

In words, the probability of drawing an atypical distribution is bounded by a function of the KL divergence 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, then

Technical statement

Define:

Then, Sanov's theorem states: [1]

Here, means the interior, and means the closure.

References

  1. Dembo, Amir; Zeitouni, Ofer (2010). "Large Deviations Techniques and Applications" . Stochastic Modelling and Applied Probability. 38: 16–17. doi:10.1007/978-3-642-03311-7. ISBN   978-3-642-03310-0. ISSN   0172-4568.

Further reading