• Corpus ID: 52163661

# Change-Point Computation for Large Graphical Models: A Scalable Algorithm for Gaussian Graphical Models with Change-Points

@article{Bybee2018ChangePointCF,
title={Change-Point Computation for Large Graphical Models: A Scalable Algorithm for Gaussian Graphical Models with Change-Points},
author={Leland Bybee and Yves F. Atchad{\'e}},
journal={J. Mach. Learn. Res.},
year={2018},
volume={19},
pages={11:1-11:38}
}
• Published 13 July 2017
• Computer Science
• J. Mach. Learn. Res.
Graphical models with change-points are computationally challenging to fit, particularly in cases where the number of observation points and the number of nodes in the graph are large. Focusing on Gaussian graphical models, we introduce an approximate majorize-minimize (MM) algorithm that can be useful for computing change-points in large graphical models. The proposed algorithm is an order of magnitude faster than a brute force search. Under some regularity conditions on the data generating…

## Figures and Tables from this paper

Online detection of local abrupt changes in high-dimensional Gaussian graphical models
• Mathematics
ArXiv
• 2020
A novel test is developed that is based on the $\ell_\infty$ norm of the normalized covariance matrix of an appropriately selected portion of incoming data and illustrates the good performance of the proposed detection procedure both in terms of computational and statistical efficiency across numerous experimental settings.
Detecting multiple change-points in the time-varying Ising model
• Computer Science
ArXiv
• 2019
A new optimization program consisting in the minimization of a penalized negative conditional log-likelihood is proposed, which gives a change-point consistency theorem, the first to present such theoretical result in the context of time-varying Ising model.
Parameter estimation for high dimensional change point regression models without grid search
• Computer Science
• 2018
An L1 regularized estimator is proposed for the parameters of a high dimensional change point regression model and the corresponding rates of convergence for the regression as well change point estimates are provided.
Detection and estimation of parameters in high dimensional multiple change point regression models via $\ell_1/\ell_0$ regularization and discrete optimization
• Computer Science
• 2019
A top down methodology called arbitrary segmentation that proceeds in a conceptually reverse manner, which is significantly more computationally efficient than existing approaches and has the ability to agnostically detect the no change' scenario.
Segmentation of high dimensional means over multi-dimensional change points and connections to regression trees
• A. Kaul
• Mathematics, Computer Science
• 2021
This article is motivated by the objective of providing a new analytically tractable and fully frequentist framework to characterize and implement regression trees while also allowing a multivariate
Seeded Binary Segmentation: A general methodology for fast and optimal change point detection
• Computer Science
• 2020
This work shows that seeded binary segmentation leads to a near-linear time approach (i.e. linear up to a logarithmic factor) independent of the underlying number of change points, and demonstrates the methodology for high-dimensional settings with an inverse covariance change point detection problem.
A Unified Framework for Change Point Detection in High-Dimensional Linear Models
• Computer Science
Statistica Sinica
• 2022
A framework for structural break detection which is suitable for a large class of models, and the proposed algorithm automatically achieves consistent parameter estimates during the change point detection process, without the need for reﬁtting the model.
Simultaneous Change Point Inference and Structure Recovery for High Dimensional Gaussian Graphical Models
• B. Liu
• Computer Science, Mathematics
• 2021
A threshold variable and an unknown threshold parameter are incorporated into a joint sparse regression model which combines p 1-regularized node-wise regression problems together and the corresponding estimated coefficients of precision matrices are obtained together.
Sequential change-point detection in high-dimensional Gaussian graphical models
• Computer Science
J. Mach. Learn. Res.
• 2020
This work introduces a novel scalable online algorithm for detecting an unknown number of abrupt changes in the inverse covariance matrix of sparse Gaussian graphical models with small delay and can be extended to a large class of continuous and discrete graphical models.
Optimistic search strategy: Change point detection for large-scale data via adaptive logarithmic queries
• Computer Science
ArXiv
• 2020
It is demonstrated empirically that the optimistic search methods lead to competitive estimation performance while heavily reducing run-time, and asymptotic minimax optimality for single and multiple change point scenarios is proved.

## References

SHOWING 1-10 OF 42 REFERENCES
Computationally efficient change point detection for high-dimensional regression
• Computer Science, Mathematics
• 2016
This work proposes a joint estimator of the number and the locations of the change points and of the parameters in the corresponding segments of the data-generating process and establishes oracle inequalities for the estimator as well as for its binary search approximation.
Change point estimation in high dimensional Markov random‐field models
• Computer Science, Mathematics
Journal of the Royal Statistical Society. Series B, Statistical methodology
• 2017
The paper investigates a change point estimation problem in the context of high dimensional Markov random‐field models and derives a tight bound for the estimate, up to a logarithmic factor, even in settings where the number of possible edges in the network far exceeds the sample size.
Graph-based change-point detection
• Computer Science
• 2012
Simulations reveal that the new approach has better power than existing approaches when the dimension of the data is moderate to high, and is illustrated on two applications: the determination of authorship of a classic novel, and the detection of change in a network over time.
Model selection and estimation in the Gaussian graphical model
• Computer Science
• 2007
The implementation of the penalized likelihood methods for estimating the concentration matrix in the Gaussian graphical model is nontrivial, but it is shown that the computation can be done effectively by taking advantage of the efficient maxdet algorithm developed in convex optimization.
Sparse Nonparametric Graphical Models
• Computer Science, Mathematics
ArXiv
• 2012
Two approaches to building more flexible graphical models are discussed, one allows arbitrary graphs and a nonparametric extension of the Gaussian; the other uses kernel density estimation and restricts the graphs to trees and forests.
Model Selection Through Sparse Maximum Likelihood Estimation for Multivariate Gaussian or Binary Data
• Computer Science
J. Mach. Learn. Res.
• 2008
This work considers the problem of estimating the parameters of a Gaussian or binary distribution in such a way that the resulting undirected graphical model is sparse, and presents two new algorithms for solving problems with at least a thousand nodes in the Gaussian case.
Statistical Learning with Sparsity: The Lasso and Generalizations
• Computer Science
• 2015
Statistical Learning with Sparsity: The Lasso and Generalizations presents methods that exploit sparsity to help recover the underlying signal in a set of data and extract useful and reproducible patterns from big datasets.
Estimating networks with jumps.
• Computer Science
Electronic journal of statistics
• 2012
A procedure is proposed that estimates the structure of a graphical model by minimizing the temporally smoothed L1 penalized regression, which allows jointly estimating the partition boundaries of the VCVS model and the coefficient of the sparse precision matrix on each block of the partition.
A unified framework for high-dimensional analysis of $M$-estimators with decomposable regularizers
• Computer Science, Mathematics
NIPS
• 2009
A unified framework for establishing consistency and convergence rates for regularized M-estimators under high-dimensional scaling is provided and one main theorem is state and shown how it can be used to re-derive several existing results, and also to obtain several new results.
Consistent neighbourhood selection for sparse high-dimensional graphs with the Lasso
• Computer Science
• 2004
It is shown that the proposed neighborhood selection scheme with the Lasso is consistent for sparse high-dimensional graphs, and the consistency hinges on the choice of the penalty parameter.