Salvato in:
Dettagli Bibliografici
Autori principali: Kang, Xiaohan, Hajek, Bruce
Natura: Preprint
Pubblicazione: 2021
Soggetti:
Accesso online:https://arxiv.org/abs/2102.00055
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912418276311040
author Kang, Xiaohan
Hajek, Bruce
author_facet Kang, Xiaohan
Hajek, Bruce
contents Recovery of the causal structure of dynamic networks from noisy measurements has long been a problem of interest across many areas of science and engineering. Many algorithms have been proposed, but there is little 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 Monte Carlo estimation of receiver operating characteristic (ROC) curves based on likelihood ratio samples assuming side information is available. The estimated ROC curves and curves obtained through the use of Bhattacharyya coefficients or Kullback--Leibler divergences are also compared.
format Preprint
id arxiv_https___arxiv_org_abs_2102_00055
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Lower Bounds on Information Requirements for Causal Network Inference
Kang, Xiaohan
Hajek, Bruce
Information Theory
62A99, 62C05
G.3
Recovery of the causal structure of dynamic networks from noisy measurements has long been a problem of interest across many areas of science and engineering. Many algorithms have been proposed, but there is little 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 Monte Carlo estimation of receiver operating characteristic (ROC) curves based on likelihood ratio samples assuming side information is available. The estimated ROC curves and curves obtained through the use of Bhattacharyya coefficients or Kullback--Leibler divergences are also compared.
title Lower Bounds on Information Requirements for Causal Network Inference
topic Information Theory
62A99, 62C05
G.3
url https://arxiv.org/abs/2102.00055