Manifold Learning with Arbitrary Norms

Joe Kileel, Amit Moscovich, Nathan Zelesko, Amit Singer

Research output: Contribution to journalArticlepeer-review

9 Scopus citations


Manifold learning methods play a prominent role in nonlinear dimensionality reduction and other tasks involving high-dimensional data sets with low intrinsic dimensionality. Many of these methods are graph-based: they associate a vertex with each data point and a weighted edge with each pair. Existing theory shows that the Laplacian matrix of the graph converges to the Laplace–Beltrami operator of the data manifold, under the assumption that the pairwise affinities are based on the Euclidean norm. In this paper, we determine the limiting differential operator for graph Laplacians constructed using any norm. Our proof involves an interplay between the second fundamental form of the manifold and the convex geometry of the given norm’s unit ball. To demonstrate the potential benefits of non-Euclidean norms in manifold learning, we consider the task of mapping the motion of large molecules with continuous variability. In a numerical simulation we show that a modified Laplacian eigenmaps algorithm, based on the Earthmover’s distance, outperforms the classic Euclidean Laplacian eigenmaps, both in terms of computational cost and the sample size needed to recover the intrinsic geometry.

Original languageEnglish (US)
Article number82
JournalJournal of Fourier Analysis and Applications
Issue number5
StatePublished - Oct 2021

All Science Journal Classification (ASJC) codes

  • Analysis
  • General Mathematics
  • Applied Mathematics


  • Convex body
  • Diffusion maps
  • Dimensionality reduction
  • Laplacian eigenmaps
  • Riemannian geometry
  • Second-order differential operator


Dive into the research topics of 'Manifold Learning with Arbitrary Norms'. Together they form a unique fingerprint.

Cite this