All Dates/Times are Australian Eastern Standard Time (AEST)

Technical Program

Paper Detail

Paper IDD2-S4-T3.3
Paper Title Lower Bounds on Information Requirements for Causal Network Inference
Authors Xiaohan Kang, Bruce Hajek, University of Illinois at Urbana–Champaign, United States
Session D2-S4-T3: IT Bounds on Estimation
Chaired Session: Tuesday, 13 July, 23:00 - 23:20
Engagement Session: Tuesday, 13 July, 23:20 - 23:40
Abstract Recovery of the causal structure of dynamic networks from noisy measurements has long been a problem of intense interest across many areas of science and engineering. Many algorithms have been proposed, but there is no work that compares the performance of the algorithms to converse bounds in a non-asymptotic setting. As a step to address this problem, this paper gives lower bounds on the error probability for causal network support recovery in a linear Gaussian setting. The bounds are based on the use of the Bhattacharyya coefficient for binary hypothesis testing problems with mixture probability distributions. Comparison of the bounds and the performance achieved by two representative recovery algorithms are given for sparse random networks based on the Erdős–Rényi model.