Filters








1,756 Hits in 7.3 sec

Discovery of Causal Models that Contain Latent Variables Through Bayesian Scoring of Independence Constraints [chapter]

Fattaneh Jabbari, Joseph Ramsey, Peter Spirtes, Gregory Cooper
2017 Lecture Notes in Computer Science  
Using this constraint-based scoring method, we are able to score multiple causal models, which possibly contain latent variables, and output the most probable one.  ...  We introduce a hybrid method that derives a Bayesian probability that the set of independence tests associated with a given causal model are jointly correct.  ...  The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.  ... 
doi:10.1007/978-3-319-71246-8_9 pmid:29520396 fatcat:bmvsbtmrtbenbi5ojt3bi5jjuu

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.  ...  Most of the real-world data, however, contain a mixture of discrete and continuous variables.  ...  Bayesian Constraint-Based Causal Discovery One of the state-of-the-art algorithms in causal discovery is Bayesian Constraintbased Causal Discovery (BCCD).  ... 
doi:10.1007/978-3-319-11433-0_29 fatcat:rw7gjolyn5awnhs6uhxohnvb5u

Comparative Benchmarking of Causal Discovery Techniques [article]

Karamjit Singh, Garima Gupta, Vartika Tewari, Gautam Shroff
2017 arXiv   pre-print
In this paper we present a comprehensive view of prominent causal discovery algorithms, categorized into two main categories (1) assuming acyclic and no latent variables, and (2) allowing both cycles and  ...  For (b) and (c) we train causal Bayesian networks with structures as predicted by each causal discovery technique to carry out counterfactual or standard predictive inference.  ...  Constraint-based methods: Constraint-based algorithms learn causal Bayesian networks with conditional independence tests through analyzing the probabilistic relations entailed by the Markov property of  ... 
arXiv:1708.06246v2 fatcat:2h6vhkd5pfcfpei3o6t7rjtw3y

Towards Robust and Versatile Causal Discovery for Business Applications

Giorgos Borboudakis, Ioannis Tsamardinos
2016 Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '16  
Causal discovery algorithms can induce some of the causal relations from the data, commonly in the form of a causal network such as a causal Bayesian network.  ...  ETIO is an instance of the logical approach to integrative causal discovery that has been relatively recently introduced and enables the solution of complex reverse-engineering problems in causal discovery  ...  The main principle in the logic-based approach to causal discovery is that results of the tests of independence correspond to m-connection or m-separation constraints that should hold in the unknown causal  ... 
doi:10.1145/2939672.2939872 dblp:conf/kdd/BorboudakisT16 fatcat:6sjw5zcgjzc2bfqo3hh66xbwze

Combining Linear Non-Gaussian Acyclic Model with Logistic Regression Model for Estimating Causal Structure from Mixed Continuous and Discrete Data [article]

Chao Li, Shohei Shimizu
2018 arXiv   pre-print
In addition, we derive the BIC scoring function for model selection. The new discovery algorithm can learn causal structures from mixed continuous and discrete data without discretization.  ...  In this paper, we define a novel hybrid causal model which consists of both continuous and discrete variables.  ...  The set of all independence constraints imposed by the structure of a DAG model can be characterized by the Markov conditions, which are the constraints that each variable is independent of its non-descendants  ... 
arXiv:1802.05889v1 fatcat:4vjrnhnxrffsxovej5pt7adeaq

A Review on Algorithms for Constraint-based Causal Discovery [article]

Kui Yu, Jiuyong Li, Lin Liu
2016 arXiv   pre-print
Causal discovery studies the problem of mining causal relationships between variables from data, which is of primary interest in science.  ...  In this paper, we aim to review the constraint-based causal discovery algorithms. Firstly, we discuss the learning paradigm of the constraint-based approaches.  ...  The AIT framework modeled the problem of unreliability of statistical independence tests as a knowledge base containing a set of independence facts that are related through Pearls well-known axioms [72  ... 
arXiv:1611.03977v2 fatcat:ercpfkqssnabfgdc3ndd7bd3tu

Handling hybrid and missing data in constraint-based causal discovery to study the etiology of ADHD

Elena Sokolova, Daniel von Rhein, Jilly Naaijen, Perry Groot, Tom Claassen, Jan Buitelaar, Tom Heskes
2016 International Journal of Data Science and Analytics  
In this paper, we consider two challenges in causal discovery that occur very often when working with medical data: a mixture of discrete and continuous variables and a substantial amount of missing values  ...  Causal discovery is an increasingly important method for data analysis in the field of medical research.  ...  In this paper, we use the Bayesian Constraint-based Causal Discovery (BCCD) algorithm [10] which is a state-of-the-art algorithm for causal discovery.  ... 
doi:10.1007/s41060-016-0034-x pmid:28691055 pmcid:PMC5479362 dblp:journals/ijdsa/SokolovaRNGCBH17 fatcat:537xfzy6wjg3nolmdpmt32n33u

D'ya like DAGs? A Survey on Structure Learning and Causal Discovery [article]

Matthew J. Vowels, Necati Cihan Camgoz, Richard Bowden
2021 arXiv   pre-print
Causal reasoning is a crucial part of science and human intelligence. In order to discover causal relationships from data, we need structure discovery methods.  ...  We provide a review of background theory and a survey of methods for structure discovery.  ...  Assuming that the true structural direction is → , the concept of independent mechanisms holds that ( ) contains no information about ( | ), and vice versa.  ... 
arXiv:2103.02582v2 fatcat:x45blijl5ze5xjyuqh6vlc26oq

Causal discovery in machine learning: Theories and applications

Ana Rita Nogueira, João Gama, Carlos Abreu Ferreira
2021 Journal of Dynamics & Games  
The purpose of this survey is to present a cross-sectional view of causal discovery domain, with an emphasis in the machine learning/data mining area. 2020 Mathematics Subject Classification.  ...  Causality can be seen as a mean of predicting the future, based on information about past events, and with that, prevent or alter future outcomes.  ...  This research was carried out in the context of the project FailStopper (DSAIPA/DS/0086/2018) and supported by the Fundação para a Ciência e Tecnologia (FCT), Portugal for the PhD Grant SFRH/BD/146197/  ... 
doi:10.3934/jdg.2021008 fatcat:vh4dng5lsfcj3fydwbgy457ejm

Ancestral Causal Inference [article]

Sara Magliacane, Tom Claassen, Joris M. Mooij
2017 arXiv   pre-print
Constraint-based causal discovery from limited data is a notoriously difficult challenge due to the many borderline independence test decisions.  ...  Additionally, we propose a method to score causal predictions based on their confidence.  ...  Preliminaries and related work Preliminaries We assume that the data generating process can be modeled by a causal Directed Acyclic Graph (DAG) that may contain latent variables.  ... 
arXiv:1606.07035v3 fatcat:dnuf4u3zpnbghphyu5swmxtrtq

DAG-WGAN: Causal Structure Learning With Wasserstein Generative Adversarial Networks [article]

Hristo Petkov, Colin Hanley, Feng Dong
2022 arXiv   pre-print
and support the discovery of Directed Acyclic Graphs (DAGs) that faithfully represent the underlying data distribution.  ...  However, so far no study has investigated the use of Wasserstein distance for causal structure learning via generative models.  ...  INTRODUCTION Discovering causal relationships yields new scientific knowledge. Causal discovery involves the process of learning structures of Bayesian Networks (BN) from data.  ... 
arXiv:2204.00387v1 fatcat:mrpxiupkrndnxi6ikucfzzbfni

Causal Discovery for Manufacturing Domains [article]

Katerina Marazopoulou, Rumi Ghosh, Prasanth Lade, David Jensen
2016 arXiv   pre-print
Yield and quality improvement is of paramount importance to any manufacturing company. One of the ways of improving yield is through discovery of the root causal factors affecting yield.  ...  Standard evaluation techniques for causal structure learning shows that the learned causal models seem to closely represent the underlying latent causal relationship between different factors in the production  ...  RELATED WORK In the area of causal discovery, the constraint-based algorithms we focused on retrieve models up to the Markov equivalence class (and thus might contain undirected edges).  ... 
arXiv:1605.04056v2 fatcat:kqef7cwlqnh6fafjpivgq5jlwu

Obtaining Accurate Probabilistic Causal Inference by Post-Processing Calibration [article]

Fattaneh Jabbari, Mahdi Pakdaman Naeini, Gregory F. Cooper
2017 arXiv   pre-print
Discovery of an accurate causal Bayesian network structure from observational data can be useful in many areas of science.  ...  Our experiments on simulated data support that the proposed approach improves the calibration of causal edge predictions.  ...  Finally, there are no computationally tractable Bayesian methods for discovering CBNs that contain more than a few latent confounders; in contrast, constraint-based methods exist that can perform discovery  ... 
arXiv:1712.08626v1 fatcat:bxankr46v5emzjxwvo53valyxu

Causal Discovery of Flight Service Process Based on Event Sequence [article]

Zhiwei Xing, Lin Zhang, Huan Xia, Qian Luo, Zhao-xin Chen
2021 arXiv   pre-print
However, the existing process causal factor discovery methods only do certain research when the assumption of causal sufficiency is established and does not consider the existence of latent variables.  ...  The optimized fuzzy mining process model is used as the service benchmark model, and the local causal discovery algorithm is used to discover the causal factors.  ...  Conflicts of Interest The authors declare that they have no conflicts of interest. Acknowledgments  ... 
arXiv:2105.00866v1 fatcat:cxvyhy6kjrdlxdlju7j5chwv3y

A Hybrid Anytime Algorithm for the Constructiion of Causal Models From Sparse Data [article]

Denver Dash, Marek J. Druzdzel
2013 arXiv   pre-print
We present a hybrid constraint-based/Bayesian algorithm for learning causal networks in the presence of sparse data.  ...  The algorithm searches the space of equivalence classes of models (essential graphs) using a heuristic based on conventional constraint-based techniques.  ...  This research was supported by the Air Force Office of Scientific Research under grant number F49620-97-1-0225 to University of Pittsburgh, and by the National Science Foundation under Faculty Early Career  ... 
arXiv:1301.6689v1 fatcat:o5quapgwmbeg3nonvyh2sax2ei
« Previous Showing results 1 — 15 out of 1,756 results