English

Diffusion Maps : Using the Semigroup Property for Parameter Tuning

Machine Learning 2022-03-08 v1 Machine Learning Numerical Analysis Numerical Analysis

Abstract

Diffusion maps (DM) constitute a classic dimension reduction technique, for data lying on or close to a (relatively) low-dimensional manifold embedded in a much larger dimensional space. The DM procedure consists in constructing a spectral parametrization for the manifold from simulated random walks or diffusion paths on the data set. However, DM is hard to tune in practice. In particular, the task to set a diffusion time t when constructing the diffusion kernel matrix is critical. We address this problem by using the semigroup property of the diffusion operator. We propose a semigroup criterion for picking t. Experiments show that this principled approach is effective and robust.

Keywords

Cite

@article{arxiv.2203.02867,
  title  = {Diffusion Maps : Using the Semigroup Property for Parameter Tuning},
  author = {Shan Shan and Ingrid Daubechies},
  journal= {arXiv preprint arXiv:2203.02867},
  year   = {2022}
}

Comments

14 pages, 12 figures