Abstract
We prove the existence of a class $A$ of subsets of $\mathbb{R}^d$ of VC dimension 1 such that the symmetric convex hull $F$ of the class of characteristic functions of sets in $A$ is rich in the following sense. For any absolutely continuous probability measure $\mu$ on $\mathbb{R}^d$, measurable set $B$ and $\varepsilon \gt 0$, there exists a function $f$ in $F$ such that the measure of the symmetric difference of $B$ and the set where $f$ is positive is less than $\varepsilon$. The question was motivated by the investigation of the theoretical properties of certain algorithms in machine learning.
Citation
Gábor Lugosi. Shahar Mendelson. Vladimir Koltchinskii. "A note on the richness of convex hulls of VC classes." Electron. Commun. Probab. 8 167 - 169, 2003. https://doi.org/10.1214/ECP.v8-1097
Information