DeepAI AI Chat
Log In Sign Up

LDLE: Low Distortion Local Eigenmaps

by   Dhruv Kohli, et al.

We present Low Distortion Local Eigenmaps (LDLE), a manifold learning technique which constructs a set of low distortion local views of a dataset in lower dimension and registers them to obtain a global embedding. The local views are constructed using the global eigenvectors of the graph Laplacian and are registered using Procrustes analysis. The choice of these eigenvectors may vary across the regions. In contrast to existing techniques, LDLE is more geometric and can embed manifolds without boundary as well as non-orientable manifolds into their intrinsic dimension.


page 3

page 9

page 13

page 16

page 23

page 27

page 28

page 36


Atlas flow : compatible local structures on the manifold

In this paper, we focus on the intersections of a manifold's local struc...

A Cosine Rule-Based Discrete Sectional Curvature for Graphs

How does one generalize differential geometric constructs such as curvat...

Behavior of Graph Laplacians on Manifolds with Boundary

In manifold learning, algorithms based on graph Laplacians constructed f...

Heuristic Framework for Multi-Scale Testing of the Multi-Manifold Hypothesis

When analyzing empirical data, we often find that global linear models o...

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

Let ℳ be a smooth submanifold of ℝ^n equipped with the Euclidean (chorda...

Viewpoint distortion compensation in practical surveillance systems

Our aim is to estimate the perspective-effected geometric distortion of ...

Multi-View Kernel Consensus For Data Analysis and Signal Processing

The input data features set for many data driven tasks is high-dimension...