

























We investigate how many hyperplanes with independent standard Gaussian directions one needs to produce a $δ$-uniform tessellation of a subset $S$ of the Euclidean sphere, meaning that for any pair of points in $S$ the fraction of hyperplanes separating them corresponds to their geodesic distance up to an additive error $δ$. It was conjectured that $δ^{-2}w_*(S)^2$ Gaussian random hyperplanes are necessary and sufficient for this purpose, where $w_*(S)$ is the Gaussian complexity of $S$. We falsify this conjecture by constructing a set $S$ where $δ^{-3}w_*(S)^2$ Gaussian hyperplanes are necessary and sufficient.
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。