English

Beyond Black Box Densities: Parameter Learning for the Deviated Components

Machine Learning 2022-10-28 v2 Machine Learning Statistics Theory Statistics Theory

Abstract

As we collect additional samples from a data population for which a known density function estimate may have been previously obtained by a black box method, the increased complexity of the data set may result in the true density being deviated from the known estimate by a mixture distribution. To model this phenomenon, we consider the \emph{deviating mixture model} (1λ)h0+λ(i=1kpif(xθi))(1-\lambda^{*})h_0 + \lambda^{*} (\sum_{i = 1}^{k} p_{i}^{*} f(x|\theta_{i}^{*})), where h0h_0 is a known density function, while the deviated proportion λ\lambda^{*} and latent mixing measure G=i=1kpiδθiG_{*} = \sum_{i = 1}^{k} p_{i}^{*} \delta_{\theta_i^{*}} associated with the mixture distribution are unknown. Via a novel notion of distinguishability between the known density h0h_{0} and the deviated mixture distribution, we establish rates of convergence for the maximum likelihood estimates of λ\lambda^{*} and GG^{*} under Wasserstein metric. Simulation studies are carried out to illustrate the theory.

Keywords

Cite

@article{arxiv.2202.02651,
  title  = {Beyond Black Box Densities: Parameter Learning for the Deviated Components},
  author = {Dat Do and Nhat Ho and XuanLong Nguyen},
  journal= {arXiv preprint arXiv:2202.02651},
  year   = {2022}
}

Comments

Accepted at NeurIPS 2022. Dat Do and Nhat Ho contributed equally to this work

R2 v1 2026-06-24T09:22:05.480Z