Ph.D
Group : Learning and Optimization
Generative Neural Networks to Infer Causal Mechanisms: Algorithms and Applications
Starts on 01/01/2017
Advisor : GUYON, Isabelle
Funding : contrat doctoral UPS
Affiliation : Université Paris-Saclay
Laboratory : LRI - amphithéâtre Shannon du Bâtiment 660
Defended on 17/12/2019, committee :
Kristin Bennett, Professeur, Rensselaer Polytechnic Institute | Rapporteur
Kun Zhang, Assistant Professor, Carnegie Mellon University | Rapporteur
Jean-Pierre Nadal, Directeur de Recherche au CNRS, École Normale Supérieure | Examinateur
Julie Josse, Professeur, CMAP & INRIA | Examinateur
Research activities :
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 independencies and simplicity of the causal mechanisms through two algorithms. Extensive experiments on both simulated and real-world data and a throughout theoretical analysis prove the good performance and the soundness of the proposed approaches.
