ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2207.06074
17
9

Optimal Reach Estimation and Metric Learning

13 July 2022
Eddie Aamari
Clément Berenfeld
Clément Levrard
ArXivPDFHTML
Abstract

We study the estimation of the reach, an ubiquitous regularity parameter in manifold estimation and geometric data analysis. Given an i.i.d. sample over an unknown ddd-dimensional Ck\mathcal{C}^kCk-smooth submanifold of RD\mathbb{R}^DRD, we provide optimal nonasymptotic bounds for the estimation of its reach. We build upon a formulation of the reach in terms of maximal curvature on one hand, and geodesic metric distortion on the other hand. The derived rates are adaptive, with rates depending on whether the reach of MMM arises from curvature or from a bottleneck structure. In the process, we derive optimal geodesic metric estimation bounds.

View on arXiv
Comments on this paper