pith. sign in

arxiv: 1706.09446 · v1 · pith:TYBYOCZDnew · submitted 2017-06-28 · 🧮 math.PR · math.FA

On the tightness of Gaussian concentration for convex functions

classification 🧮 math.PR math.FA
keywords gammaalphageqslantleqslantconcentrationconstantsconvexfrac
0
0 comments X
read the original abstract

The concentration of measure phenomenon in Gauss' space states that every $L$-Lipschitz map $f$ on $\mathbb R^n$ satisfies \[ \gamma_{n} \left(\{ x : | f(x) - M_{f} | \geqslant t \} \right) \leqslant 2 e^{ - \frac{t^2}{ 2L^2} }, \quad t>0, \] where $\gamma_{n} $ is the standard Gaussian measure on $\mathbb R^{n}$ and $M_{f}$ is a median of $f$. In this work, we provide necessary and sufficient conditions for when this inequality can be reversed, up to universal constants, in the case when $f$ is additionally assumed to be convex. In particular, we show that if the variance ${\rm Var}(f)$ (with respect to $\gamma_{n}$) satisfies $ \alpha L \leqslant \sqrt{ {\rm Var}(f) } $ for some $ 0<\alpha \leqslant 1$, then \[ \gamma_{n} \left(\{ x : | f(x) - M_{f} | \geqslant t \}\right) \geqslant c e^{ -C \frac{t^2}{ L^2} } , \quad t>0 ,\] where $c,C>0$ are constants depending only on $\alpha$.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.