This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision | ||
world:log-sobolev [2025/07/09 10:58] rdouc [Theorem] |
world:log-sobolev [2025/07/09 11:02] (current) rdouc [Concentration inequalities and logarithmic Sobolev inequality] |
||
---|---|---|---|
Line 1: | Line 1: | ||
- | ====== Concentration inequalities and logarithmic Sobolev inequality ====== | + | ====== Logarithmic Sobolev inequality and concentration ====== |
$\newcommand{\Ent}{\mathrm{Ent}}$ | $\newcommand{\Ent}{\mathrm{Ent}}$ | ||
- | ====== Theorem (Thm 7.4.1 in the book "Sur les inégalités de Sobolev logarithmiques")====== | + | ====== Theorem ====== |
+ | * Taken from Thm 7.4.1 in the book "Sur les inégalités de Sobolev logarithmiques". | ||
+ | <WRAP center round tip 80%> | ||
Let $\mu$ be a probability measure on $\mathbb{R}^n$ satisfying the following logarithmic Sobolev inequality: | Let $\mu$ be a probability measure on $\mathbb{R}^n$ satisfying the following logarithmic Sobolev inequality: | ||
$$ | $$ | ||
Line 13: | Line 15: | ||
\mu(|F - \mathbb{E}_\mu(F)| \geq r) \leq 2 \exp\left(-\frac{r^2}{c}\right). | \mu(|F - \mathbb{E}_\mu(F)| \geq r) \leq 2 \exp\left(-\frac{r^2}{c}\right). | ||
$$ | $$ | ||
+ | |||
+ | </WRAP> | ||
===== Proof. ===== | ===== Proof. ===== |