Partially Linear Additive Gaussian Graphical Models

Abstract

We propose a partially linear additive Gaussian graphical model (PLA-GGM) for the estimation of associations between random variables distorted by observed confounders. Model parameters are estimated using an $L_1$-regularized maximal pseudo-profile likelihood estimator (MaPPLE) for which we prove a $\sqrt{n}$-sparsistency. Importantly, our approach avoids parametric constraints on the effects of confounders on the estimated graphical model structure. Empirically, the PLA-GGM is applied to both synthetic and real-world datasets, demonstrating superior performance compared to competing methods.

Cite

Text

Geng et al. "Partially Linear Additive Gaussian Graphical Models." International Conference on Machine Learning, 2019.

Markdown

[Geng et al. "Partially Linear Additive Gaussian Graphical Models." International Conference on Machine Learning, 2019.](https://mlanthology.org/icml/2019/geng2019icml-partially/)

BibTeX

@inproceedings{geng2019icml-partially,
  title     = {{Partially Linear Additive Gaussian Graphical Models}},
  author    = {Geng, Sinong and Yan, Minhao and Kolar, Mladen and Koyejo, Sanmi},
  booktitle = {International Conference on Machine Learning},
  year      = {2019},
  pages     = {2180-2190},
  volume    = {97},
  url       = {https://mlanthology.org/icml/2019/geng2019icml-partially/}
}