Causal Network Inference Via Group Sparse Regularization

DOI10.1109/TSP.2011.2129515MaRDI QIDQ4572984zbMATH OpenOpenAlexWikidataFDO

Authors Andrew K. Bolstad, Barry D. Van Veen, Robert D. Nowak

Publication date 18 July 2018

Published in IEEE Transactions on Signal Processing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1106.0762

Mathematics Subject Classification ID

Ridge regression; shrinkage estimators (Lasso) (62J07) Deterministic network models in operations research (90B10) Communication theory (94A05)

Abstract: This paper addresses the problem of inferring sparse causal networks modeled by multivariate auto-regressive (MAR) processes. Conditions are derived under which the Group Lasso (gLasso) procedure consistently estimates sparse network structure. The key condition involves a "false connection score." In particular, we show that consistent recovery is possible even when the number of observations of the network is far less than the number of parameters describing the network, provided that the false connection score is less than one. The false connection score is also demonstrated to be a useful metric of recovery in non-asymptotic regimes. The conditions suggest a modified gLasso procedure which tends to improve the false connection score and reduce the chances of reversing the direction of causal influence. Computational experiments and a real network based electrocorticogram (ECoG) simulation study demonstrate the effectiveness of the approach.

Cited in

(13)

• Dynamic networks with multi-scale temporal structure
• A novel Granger causality method based on HSIC-Lasso for revealing nonlinear relationship between multivariate time series
• A scalable multi-step least squares method for network identification with unknown disturbance topology
• From dynamics to links: a sparse reconstruction of the topology of a neural network
• Sparse network identifiability via compressed sensing
• Operator-valued kernel-based vector autoregressive models for network inference
• Blind Identification of Stochastic Block Models from Dynamical Observations
• Inferred networks and the social determinants of health
• The analysis of alternating minimization method for double sparsity constrained optimization problem
• Online graph topology learning from matrix-valued time series
• Neighborhood VAR: efficient estimation of multivariate time series with neighborhood information
• Mixed norm regularized recursive total least squares for group sparse system identification
• Network inference and biological dynamics

This page was built for publication: Causal Network Inference Via Group Sparse Regularization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4572984)