Lower Bounds on the Low-Distortion Embedding Dimension of Submanifolds of ℝ^n

05/28/2021
by   Mark A. Iwen, et al.
0

Let ℳ be a smooth submanifold of ℝ^n equipped with the Euclidean (chordal) metric. This note considers the smallest dimension m for which there exists a bi-Lipschitz function f: ℳ↦ℝ^m with bi-Lipschitz constants close to one. The main result bounds the embedding dimension m below in terms of the bi-Lipschitz constants of f and the reach, volume, diameter, and dimension of ℳ. This new lower bound is applied to show that prior upper bounds by Eftekhari and Wakin (arXiv:1306.4748) on the minimal low-distortion embedding dimension of such manifolds using random matrices achieve near-optimal dependence on both reach and volume. This supports random linear maps as being nearly as efficient as the best possible nonlinear maps at reducing the ambient dimension for manifold data. In the process of proving our main result, we also prove similar results concerning the impossibility of achieving better nonlinear measurement maps with the Restricted Isometry Property (RIP) in compressive sensing applications.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/08/2018

Nonlinear Dimension Reduction via Outer Bi-Lipschitz Extensions

We introduce and study the notion of an outer bi-Lipschitz extension of ...
research
10/08/2021

On Fast Johnson-Lindenstrauss Embeddings of Compact Submanifolds of ℝ^N with Boundary

Let ℳ be a smooth d-dimensional submanifold of ℝ^N with boundary that's ...
research
12/13/2017

Fractal dimension and lower bounds for geometric problems

We study the complexity of geometric problems on spaces of low fractal d...
research
05/04/2016

The embedding dimension of Laplacian eigenfunction maps

Any closed, connected Riemannian manifold M can be smoothly embedded by ...
research
09/14/2022

Small Transformers Compute Universal Metric Embeddings

We study representations of data from an arbitrary metric space 𝒳 in the...
research
10/11/2019

Fitting a manifold of large reach to noisy data

Let M⊂R^n be a C^2-smooth compact submanifold of dimension d. Assume tha...
research
01/26/2021

LDLE: Low Distortion Local Eigenmaps

We present Low Distortion Local Eigenmaps (LDLE), a manifold learning te...

Please sign up or login with your details

Forgot password? Click here to reset