English

Landmark Diffusion Maps (L-dMaps): Accelerated manifold learning out-of-sample extension

Machine Learning 2019-06-04 v1 Soft Condensed Matter

Abstract

Diffusion maps are a nonlinear manifold learning technique based on harmonic analysis of a diffusion process over the data. Out-of-sample extensions with computational complexity O(N)\mathcal{O}(N), where NN is the number of points comprising the manifold, frustrate applications to online learning applications requiring rapid embedding of high-dimensional data streams. We propose landmark diffusion maps (L-dMaps) to reduce the complexity to O(M)\mathcal{O}(M), where MNM \ll N is the number of landmark points selected using pruned spanning trees or k-medoids. Offering (N/M)(N/M) speedups in out-of-sample extension, L-dMaps enables the application of diffusion maps to high-volume and/or high-velocity streaming data. We illustrate our approach on three datasets: the Swiss roll, molecular simulations of a C24_{24}H50_{50} polymer chain, and biomolecular simulations of alanine dipeptide. We demonstrate up to 50-fold speedups in out-of-sample extension for the molecular systems with less than 4% errors in manifold reconstruction fidelity relative to calculations over the full dataset.

Keywords

Cite

@article{arxiv.1706.09396,
  title  = {Landmark Diffusion Maps (L-dMaps): Accelerated manifold learning out-of-sample extension},
  author = {Andrew W. Long and Andrew L. Ferguson},
  journal= {arXiv preprint arXiv:1706.09396},
  year   = {2019}
}

Comments

Submitted

R2 v1 2026-06-22T20:32:30.123Z