Filters








116,337 Hits in 5.7 sec

Direct Estimation of Differences in Causal Graphs [article]

Yuhao Wang, Chandler Squires, Anastasiya Belyaeva, Caroline Uhler
2018 arXiv   pre-print
We consider the problem of estimating the differences between two causal directed acyclic graph (DAG) models with a shared topological order given i.i.d. samples from each model.  ...  This is of interest for example in genomics, where changes in the structure or edge weights of the underlying causal graphs reflect alterations in the gene regulatory networks.  ...  Introduction Directed acyclic graph (DAG) models, also known as Bayesian networks, are widely used to model causal relationships in complex systems.  ... 
arXiv:1802.05631v3 fatcat:ca74znz3yzad3dcr3wxsspntfu

Smooth information flow in temperature climate network reflects mass transport

Jaroslav Hlinka, Nikola Jajcay, David Hartman, Milan Paluš
2017 Chaos  
In this paper we investigate the possibility of inferring the causal climate network with the explicit direction of causal influence, taking the conservative approach of linear Granger causality applied  ...  To assess the significance of this observation, we designed random graph models for climate networks and quantitatively compared the temperature causal network with prevailing wind direction.  ...  P103/11/J068 and by the Ministry of Education, Youth and Sports of the Czech Republic within the Program KONTAKT II, project LH14001.  ... 
doi:10.1063/1.4978028 pmid:28364752 fatcat:qffnlnpmvzho5ecbhe52mbdbum

DCI: Learning Causal Differences between Gene Regulatory Networks [article]

Anastasiya Belyaeva, Chandler Squires, Caroline Uhler
2020 bioRxiv   pre-print
This algorithm is efficient in its use of samples and computation since it infers the differences between causal graphs directly without estimating each possibly large causal graph separately.  ...  We provide a user-friendly Python implementation of DCI and also enable the user to learn the most robust difference causal graph across different tuning parameters via stability selection.  ...  In this paper, we describe the difference causal inference (DCI ) algorithm for direct estimation of the difference causal graph based on observational data from two conditions.  ... 
doi:10.1101/2020.05.13.093765 fatcat:fljdkgeisjh3dfgvflw4zjyyw4

DoWhy: Addressing Challenges in Expressing and Validating Causal Assumptions [article]

Amit Sharma, Vasilis Syrgkanis, Cheng Zhang, Emre Kıcıman
2021 arXiv   pre-print
Violation of any of these assumptions leads to significant error in the effect estimate.  ...  Our experience with DoWhy highlights a number of open questions for future research: developing new ways beyond causal graphs to express assumptions, the role of causal discovery in learning relevant parts  ...  Both these graphs can be used to identify the effect and construct an estimator, and the differences in the resultant estimates will help understand the significance of the different causal assumptions  ... 
arXiv:2108.13518v1 fatcat:zlsqcpmfmnflvdt5djxddok6ee

Causal Directed Acyclic Graphs and the Direction of Unmeasured Confounding Bias

Tyler J. VanderWeele, Miguel A. Hernán, James M. Robins
2008 Epidemiology  
The results are given within the context of the directed acyclic graph causal framework and are stated in terms of signed edges. Rigorous definitions for signed edges are provided.  ...  We describe cases in which intuition concerning signed edges fails and we characterize the directed acyclic graphs that researchers can use to draw conclusions about the sign of the bias of unmeasured  ...  Similarly, if the estimated risk difference controlling only for X is positive and the conditions in (ii) are satisfied, then the estimate of the risk difference is an underestimate of the true causal  ... 
doi:10.1097/ede.0b013e3181810e29 pmid:18633331 pmcid:PMC4242711 fatcat:2vxllsv2vvf4hldqqozmzlaf2a

Review of Causal Discovery Methods Based on Graphical Models

Clark Glymour, Kun Zhang, Peter Spirtes
2019 Frontiers in Genetics  
A fundamental task in various disciplines of science, including biology, is to find underlying causal relations and make use of them.  ...  This paper aims to give a introduction to and a brief review of the computational methods for causal discovery that were developed in the past three decades, including constraint-based and score-based  ...  AUTHOR CONTRIBUTIONS All authors listed have made a substantial, direct and intellectual contribution to the work, and approved it for publication.  ... 
doi:10.3389/fgene.2019.00524 pmid:31214249 pmcid:PMC6558187 fatcat:q2ruix27tjcc3b4oze4y7223by

IDA with Background Knowledge

Zhuangyan Fang, Yangbo He
2020 Conference on Uncertainty in Artificial Intelligence  
In this paper, we consider the problem of estimating all possible causal effects from observational data with two types of background knowledge: direct causal information and nonancestral information.  ...  Based on the proposed rules, we present a fully local algorithm to estimate all possible causal effects with direct causal information.  ...  This research was supported by National Key R&D Program of China (2018YFB1004300) and NSFC (11671020).  ... 
dblp:conf/uai/FangH20 fatcat:hwttgwdp2zclzny3hgawtqsjbe

Causal Discovery from Databases with Discrete and Continuous Variables [chapter]

Elena Sokolova, Perry Groot, Tom Claassen, Tom Heskes
2014 Lecture Notes in Computer Science  
Bayesian Constraint-based Causal Discovery (BCCD) is a state-of-the-art method for robust causal discovery in the presence of latent variables.  ...  It combines probabilistic estimation of Bayesian networks over subsets of variables with a causal logic to infer causal statements. Currently BCCD is limited to discrete or Gaussian variables.  ...  To represent the members of this equivalence class, a different type of structure is used, known as a partially directed acyclic graph (PDAG).  ... 
doi:10.1007/978-3-319-11433-0_29 fatcat:rw7gjolyn5awnhs6uhxohnvb5u

Evaluation of Causal Structure Learning Algorithms via Risk Estimation [article]

Marco F. Eigenmann, Sach Mukherjee, Marloes H. Maathuis
2020 arXiv   pre-print
We formalize the problem in a decision-theoretic framework, via a notion of expected loss or risk for the causal setting.  ...  Recent years have seen many advances in methods for causal structure learning from data. The empirical assessment of such methods, however, is much less developed.  ...  SM is a member of the German Bundesministerium für Bildung und Forschung (BMBF) consortium "MechML".  ... 
arXiv:2006.15387v1 fatcat:zzocj22ujvhoto67pp7bo7uzki

Orthogonal Structure Search for Efficient Causal Discovery from Observational Data [article]

Anant Raj and Luigi Gresele and Michel Besserve and Bernhard Schölkopf and Stefan Bauer
2020 arXiv   pre-print
The problem of inferring the direct causal parents of a response variable among a large set of explanatory variables is of high practical importance in many disciplines.  ...  Recent work exploits stability of regression coefficients or invariance properties of models across different experimental conditions for reconstructing the full causal graph.  ...  in a directed acyclic graph.  ... 
arXiv:1903.02456v2 fatcat:3dulhzoqtbbkncjmewcdwjul24

Causal conditioning and instantaneous coupling in causality graphs [article]

Pierre-Olivier Amblard, Olivier J. J. Michel
2012 arXiv   pre-print
We particularly insist on the implication of two notions of causality that may occur in physical systems.  ...  The paper investigates the link between Granger causality graphs recently formalized by Eichler and directed information theory developed by Massey and Kramer.  ...  Figure 1 : 1 Causality graphs for the example developed in the text. Illustration of the difference between the two definitions of instantaneous causality.  ... 
arXiv:1203.5572v1 fatcat:tskwkkfewzep5cdin5jcc6jif4

Transfer Learning for Performance Modeling of Configurable Systems: A Causal Analysis [article]

Mohammad Ali Javidian, Pooyan Jamshidi, Marco Valtorta
2019 arXiv   pre-print
In this work, we investigate identifiability and transportability of causal effects and statistical relations in highly-configurable systems.  ...  Our causal analysis agrees with previous exploratory analysis Jamshidi17 and confirms that the causal effects of configuration options can be carried over across environments with high confidence.  ...  Causal Graphs A causal graphical model is a special type of graphical model in which edges are interpreted as direct causal effects.  ... 
arXiv:1902.10119v1 fatcat:wkxhnagyofb6bjjrbtii7mmhui

How Mega Is the Mega? Measuring the Spillover Effects of WeChat by Machine Learning and Econometrics

Jinyang Zheng, Zhengling Qi, Yong Tan
2016 Social Science Research Network  
estimating causal effects.  ...  Our work estimates the spillover effects of WeChat on the other top-50 most frequently used apps in China through data on users' weekly app usage.  ...  In addition, the graph of Sample 2 in Week 3 shows additional causal paths, including a direct causal effect on App 4.  ... 
doi:10.2139/ssrn.2842138 fatcat:gog3g6spdjfrjkq66ycrbyqpca

Estimating causal effects of time-dependent exposures on a binary endpoint in a high-dimensional setting

Vahé Asvatourian, Clélia Coutzac, Nathalie Chaput, Caroline Robert, Stefan Michiels, Emilie Lanoy
2018 BMC Medical Research Methodology  
Conclusions: The COPC-algorithm provided CPDAGs that keep the chronological structure present in the data and thus allowed to estimate lower bounds of the causal effect of time-dependent immunological  ...  Bidirected edges were less present in CPDAGs obtained with the COPC-algorithm, supporting the fact that there was less variability in causal effects estimated from these CPDAGs.  ...  Availability of data and materials The National Commission of Informatics and Liberties (CNIL) which is the French data protection authority, does not allow us to make these data publicly available. 5  ... 
doi:10.1186/s12874-018-0527-5 pmid:29969993 pmcid:PMC6029422 fatcat:dmclicyvvzaa5in3flwek62tvq

Causal inference of brain connectivity from fMRI with ψ-Learning Incorporated Linear non-Gaussian Acyclic Model (ψ-LiNGAM) [article]

Aiying Zhang, Gemeng Zhang, Biao Cai, Wenxing Hu, Li Xiao, Tony W. Wilson, Julia M. Stephen, Vince D. Calhoun, Yu-Ping Wang
2020 arXiv   pre-print
Directed acyclic graph (DAG) models have been applied in recent FC studies but often encountered problems such as limited sample sizes and large number of variables (namely high-dimensional problems),  ...  Our simulation results demonstrate that the proposed method is more robust and accurate than several existing ones in detecting graph structure and direction.  ...  To acquire the prior knowledge, we estimate the undirected graph first, since the skeleton of the directed graph is always included in it.  ... 
arXiv:2006.09536v1 fatcat:qtrcdlqkhba5xbk4urfm22wll4
« Previous Showing results 1 — 15 out of 116,337 results