翻訳と辞書
Words near each other
・ Sans Pression
・ Sans rival
・ Sans Sault Formation
・ Sans Soleil
・ Sanor
・ Sanor Longsawang
・ Sanora Babb
・ Sanosara
・ Sanoshi Station
・ Sanostee, New Mexico
・ Sanoth
・ Sanoura
・ Sanous
・ Sanoussi Jackou
・ Sanoussi Touré
Sanov's theorem
・ Sanowangthali
・ Sanoyas Hishino Meisho
・ Sanoyie
・ Sanpa
・ Sanpada
・ Sanpada College of Commerce and Technology
・ Sanpada railway station
・ Sanpai
・ Sanpaku
・ Sanpale
・ Sanpaolo IMI
・ Sanpasaurus
・ Sanpei Shirato
・ Sanpete County, Utah


Dictionary Lists
翻訳と辞書 辞書検索 [ 開発暫定版 ]
スポンサード リンク

Sanov's theorem : ウィキペディア英語版
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_, of the samples falls within the set ''A''—formally, we write \ \in A\}. Then,
:q^n(x^n) \le (n+1)^ 2^,
where
* q^n(x^n) is shorthand for q(x_1)q(x_2) \cdots q(x_n), and
* p^
* is the information projection of ''q'' onto ''A''.
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_\frac\log q^n(x^n) = -D_{\mathrm{KL}}(p^
*||q).
==References==

*
*Sanov, I. N. (1957) "On the probability of large deviations of random variables". ''Mat. Sbornik'' 42, 11–44.
Category:Probabilistic inequalities

抄文引用元・出典: フリー百科事典『 ウィキペディア(Wikipedia)
ウィキペディアで「Sanov's theorem」の詳細全文を読む



スポンサード リンク
翻訳と辞書 : 翻訳のためのインターネットリソース

Copyright(C) kotoba.ne.jp 1997-2016. All Rights Reserved.