Skip to Main content Skip to Navigation

Generative Neural networks to infer Causal Mechanisms: Algorithms and applications

Abstract : Causal discovery is of utmost importance for agents who must plan, reason and decide based on observations; where mistaking correlation with causation might lead to unwanted consequences. The gold standard to discover causal relations is to perform experiments. However, experiments are in many cases expensive, unethical, or impossible to realize. In these situations, there is a need for observational causal discovery, that is, the estimation of causal relations from observations alone. Causal discovery in the observational data setting traditionally involves making significant assumptions on the data and on the underlying causal model. This thesis aims to alleviate some of the assumptions made on the causal models by exploiting the modularity and expressiveness of neural networks for causal discovery, leveraging both conditional independences and simplicity of the causal mechanisms through two algorithms. Extensive experiments on both simulated and real-world data and a throughout theoretical anaylsis prove the good performance and the soundness of the proposed approaches.
Complete list of metadata

Cited literature [141 references]  Display  Hide  Download
Contributor : Diviyan Kalainathan <>
Submitted on : Sunday, January 12, 2020 - 1:32:50 AM
Last modification on : Saturday, May 1, 2021 - 3:46:46 AM
Long-term archiving on: : Monday, April 13, 2020 - 12:26:36 PM


Files produced by the author(s)


  • HAL Id : tel-02435986, version 1


Diviyan Kalainathan. Generative Neural networks to infer Causal Mechanisms: Algorithms and applications. Machine Learning [stat.ML]. Université Paris Sud (Paris 11) - Université Paris Saclay, 2019. English. ⟨tel-02435986⟩



Record views


Files downloads