基于扩散的局部固有维数估计的极小极大下界
Minimax Lower Bound for Estimating Diffusion-based Local Intrinsic Dimension
- Seoul National University(首尔大学)
机构由 AI 辅助整理,请以论文原文为准。
AI总结:
本文针对基于扩散的局部固有维数估计问题,在正则流形模型下建立了极小极大下界,明确了有限尺度场与流形维数的偏差,为该领域的统计难度研究提供了关键理论依据。
AI中文摘要:
尽管基于扩散的方法近来已成为探究高维数据固有几何结构的有效工具,但其统计难度仍在很大程度上未被探索。本文研究了对FLIPD(Kamkari等人,2024;arXiv:2406.03537)所对应的有限总体泛函的估计,FLIPD是一种基于扩散的局部固有维数(LID)量,通过高斯平滑密度的对数尺度导数定义。直观上,高斯平滑将局部维数转化为尺度定律:在d维流形附近,核质量随σ^d增长,因此对噪声尺度求导可揭示固有指数。在正则流形模型下,我们证明在该模型类上,有限尺度场与流形维数d的差异至多为O(σ^2)。随后,我们针对从n个观测值估计该有限尺度场的问题,建立了阶为(nσ^d)^{-1}的极小极大下界,适用范围为n^{-1/(2α+d)}≲σ≤σ₀。在我们的下界构造所覆盖的最小尺度下,该下界退化为非参数速率n^{-2α/(2α+d)}。
英文摘要:
While diffusion-based methods have recently emerged as effective tools for probing the intrinsic geometry of high-dimensional data, their statistical difficulty remains largely unexplored. We study estimation of the finite-scale population functional underlying FLIPD (Kamkari et al., 2024; arXiv:2406.03537), a diffusion-based local intrinsic dimension (LID) quantity defined through the logarithmic scale derivative of a Gaussian-smoothed density. Intuitively, Gaussian smoothing turns local dimension into a scale law: near a $d$-dimensional manifold, the kernel mass grows like $σ^d$, so differentiating with respect to the noise scale reveals the intrinsic exponent. Under a regular manifold model, we show uniformly over the model class that the finite-scale field differs from the manifold dimension $d$ by at most $O(σ^2)$. We then establish a minimax lower bound of order $(nσ^d)^{-1}$ for estimating this finite-scale field from $n$ observations, for $n^{-1/(2α+d)}\lesssimσ\leσ_0$. At the smallest scale covered by our lower-bound construction, the bound becomes the nonparametric rate $n^{-2α/(2α+d)}$.