English

Identifiability and Estimation in High-Dimensional Nonparametric Latent Structure Models

Statistics Theory 2025-08-06 v2 Statistics Theory

Abstract

This paper studies the problems of identifiability and estimation in high-dimensional nonparametric latent structure models. We introduce an identifiability theorem that generalizes existing conditions, establishing a unified framework applicable to diverse statistical settings. Our results rigorously demonstrate how increased dimensionality, coupled with diversity in variables, inherently facilitates identifiability. For the estimation problem, we establish near-optimal minimax rate bounds for the high-dimensional nonparametric density estimation under latent structures with smooth marginals. Contrary to the conventional curse of dimensionality, our sample complexity scales only polynomially with the dimension. Additionally, we develop a perturbation theory for component recovery and propose a recovery procedure based on simultaneous diagonalization.

Keywords

Cite

@article{arxiv.2506.09165,
  title  = {Identifiability and Estimation in High-Dimensional Nonparametric Latent Structure Models},
  author = {Yichen Lyu and Pengkun Yang},
  journal= {arXiv preprint arXiv:2506.09165},
  year   = {2025}
}
R2 v1 2026-07-01T03:09:59.708Z