English

Central Limit Theorems for Classical Multidimensional Scaling

Methodology 2019-05-15 v4

Abstract

Classical multidimensional scaling is a widely used method in dimensionality reduction and manifold learning. The method takes in a dissimilarity matrix and outputs a low-dimensional configuration matrix based on a spectral decomposition. In this paper, we present three noise models and analyze the resulting configuration matrices, or embeddings. In particular, we show that under each of the three noise models the resulting embedding gives rise to a central limit theorem. We also provide compelling simulations and real data illustrations of these central limit theorems. This perturbation analysis represents a significant advancement over previous results regarding classical multidimensional scaling behavior under randomness.

Keywords

Cite

@article{arxiv.1804.00631,
  title  = {Central Limit Theorems for Classical Multidimensional Scaling},
  author = {Gongkai Li and Minh Tang and Nichlas Charon and Carey E Priebe},
  journal= {arXiv preprint arXiv:1804.00631},
  year   = {2019}
}

Comments

26 pages, 6 figures

R2 v1 2026-06-23T01:11:49.725Z