• Corpus ID: 237635160

# Joint Estimation and Inference for Multi-Experiment Networks of High-Dimensional Point Processes

@inproceedings{Wang2021JointEA,
title={Joint Estimation and Inference for Multi-Experiment Networks of High-Dimensional Point Processes},
author={Xu Wang and Ali Shojaie},
year={2021}
}
• Published 23 September 2021
• Computer Science
Modern high-dimensional point process data, especially those from neuroscience experiments, often involve observations from multiple conditions and/or experiments. Networks of interactions corresponding to these conditions are expected to share many edges, but also exhibit unique, condition-specific ones. However, the degree of similarity among the networks from different conditions is generally unknown. Existing approaches for multivariate point processes do not take these structures into…
1 Citations

## Figures from this paper

• Computer Science
WIREs Computational Statistics
• 2022
This manuscript surveys recent work on statistical inference of joint Gaussian graphical models, identifying model structures that fit various data generation processes.

## References

SHOWING 1-10 OF 69 REFERENCES

• Computer Science, Economics
ArXiv
• 2020
A high-dimensional statistical inference procedure with theoretical guarantees for multivariate Hawkes process is proposed, using a new concentration inequality on the first and second-order statistics for integrated stochastic processes, which summarizes the entire history of the process.
• Computer Science, Mathematics
Journal of the Royal Statistical Society. Series B, Statistical methodology
• 2016
A kernel‐based method is proposed for jointly estimating all graphical models in high dimensions that characterizes the strength that one can borrow across different individuals and the effect of data dependence on parameter estimation.
• Computer Science
Biometrics
• 2017
A Bayesian neighborhood selection method to estimate Gaussian Graphical Models (GGMs) is proposed and the graph selection consistency of this method is shown, in the sense that the posterior probability of the true model converges to one.
• Computer Science
Electronic Journal of Statistics
• 2020
It is proved that under certain regularity conditions, the proposed $\ell_0$-penalized maximum likelihood estimator converges in Frobenius norm to the adjacency matrices consistent with the data-generating distributions and has the correct sparsity.
• Computer Science
Journal of the American Statistical Association
• 2022
This work proposes a new and flexible class of nonstationary Hawkes processes that allow both excitatory and inhibitory effects and estimates the latent network structure using an efficient sparse least squares estimation approach.
• Computer Science
Journal of the American Statistical Association
• 2015
This article addresses the problem of inferring multiple undirected networks in situations where some of the networks may be unrelated, while others share common features, and proposes a Bayesian approach to inference on multiple Gaussian graphical models.
• Computer Science, Mathematics
Biometrika
• 2011
An estimator forGaussian graphical models appropriate for data from several graphical models that share the same variables and some of the dependence structure is developed, aiming to preserve the common structure, while allowing for differences between the categories.
• Computer Science
Statistica Sinica
• 2016
The results indicate that the patients with poor prognostic subtype lack some important links among the genes in the apoptosis pathway, and the proposed joint estimation methods outperform other methods in graph structure recovery.
• Computer Science
J. Mach. Learn. Res.
• 2016
This work develops methodology that jointly estimates multiple Gaussian graphical models, assuming that there exists prior information on how they are structurally related, and establishes consistency of the proposed method for sparse high-dimensional Gaussia graphical models.
• Computer Science
• 2015
This paper considers multivariate counting processes depending on an unknown function to be estimated by linear combinations of a fixed dictionary, and proposes an adaptive $\ell_1$-penalization methodology, where data-driven weights of the penalty are derived from new Bernstein type inequalities for martingales.