ICML 2019oral14 citations

Partially Linear Additive Gaussian Graphical Models

Sinong Geng, Minhao Yan, Mladen Kolar, Sanmi Koyejo

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.

BibTeX
@InProceedings{pmlr-v97-geng19a,
  title = 	 {Partially Linear Additive {G}aussian Graphical Models},
  author =       {Geng, Sinong and Yan, Minhao and Kolar, Mladen and Koyejo, Sanmi},
  booktitle = 	 {Proceedings of the 36th International Conference on Machine Learning},
  pages = 	 {2180--2190},
  year = 	 {2019},
  editor = 	 {Chaudhuri, Kamalika and Salakhutdinov, Ruslan},
  volume = 	 {97},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {09--15 Jun},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v97/geng19a/geng19a.pdf},
  url = 	 {https://proceedings.mlr.press/v97/geng19a.html},
  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.}
}
Partially Linear Additive Gaussian Graphical Models · ICML 2019