Français Anglais
Accueil Annuaire Plan du site
Accueil > Evenements > Séminaires
Séminaire du LRI
Generative Neural Networks for Observational Causal Discovery
Diviyan Kalainathan

07 April 2022, 10h30 - 07 April 2022, 12h00
Salle/Bat : 2011/DIG-Moulon
Contact :

Activités de recherche : Raisonnement automatique

Résumé :
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. We will go through the traditional methods to find causal relationships in observational data: conditional independence, Occam’s razor., among others. Causal discovery in the observational data setting traditionally involves making significant assumptions on the data and on the underlying causal model. This work aims to alleviate some 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.

You can join the meeting online via Webex:
- meeting number: 2740 064 0615
- password: hVwCriMD967.

Join Webex meeting:
https://inria.webex.com/inria-en/j.php?MTID=m6744fb0489e22385e1538c4fef104f61

Or physically in the room 2011 at LISN Campus Universitaire Bât. 660 Claude Shannon - Rue René Thom, 91190 Gif-sur-Yvette.

More information at http://causaltau.github.io

Pour en savoir plus : https://causaltau.github.io/schedule/
Séminaires
TUTORIAL CODALAB - Apprenez à organiser un challen
Wednesday 13 April 2022 - 00h00
Salle : 1 - DIG-Moulon
Adrien Pavao .............................................

Generative Neural Networks for Observational Causa
Raisonnement automatique
Thursday 07 April 2022 - 10h30
Salle : 2011 - DIG-Moulon
Diviyan Kalainathan .............................................

Datamining in Epi- and Phylogenetics
Tuesday 15 March 2022 - 11h00
Salle : 455 - PCRI-N
Thomas Haschka .............................................

Répétition soutenance de thèse - Reconstructing ou
Thursday 10 March 2022 - 14h00
Salle : 455 - PCRI-N
Théophile Sanchez .............................................

An Introduction to the Boundedness Problem for Exi
Raisonnement automatique
Monday 14 February 2022 - 13h00
Salle : 455 - PCRI-N
Federico Ulliana .............................................