CAUSAL DISCOVERY PROJECT
Sponsored by CONACYT, Project A1-S-43346 (Aprendizaje de Modelos Causales)
Objectives:
The
general objective of the project is to learn causal graphical models by
integrating observational data, prior knowledge and interaction with
the environment. We are considering three application domains:
- Effective connectivity in the brain
Participants:
- Dr. L. Enrique Sucar, Research Scientist, INAOE (project director)
-
Dr. Eduardo Morales, Research Scientist, INAOE
- Dr. Felipe Orihuela-Espina, Research Scientist, INAOE
- Dr. Hugo Jair Escalante, Research Scientist, INAOE
- Dr. Julio César Muñoz-Benítez, Postdoctoral Researcher, INAOE
- MSc. Mauricio González, PhD Student, INAOE
- MSc. Verónica Rodríguez, PhD Student, INAOE
- MSc. Arquímides Méndez, PhD Student, INAOE
- Mr. Jorge Arturo Flores-López, MSc Student, INAOE
Former participants:
- Dr. Eliezer Escobar Júarez, IPN (Postdoc INAOE)
- Mr. Sebastián Bejos, (MSc CS INAOE)
- Mr. Iván Feliciano Avelino, (MSc CS INAOE)
Publications:
- Verónica Rodríguez-López, Luis Enrique Sucar, Knowledge Transfer for Learning Markov Equivalence Classes, Proceedings of the 10th International Conference on Probabilistic Graphical Models, PMLR 138:377-388, 2020. [PMLR]
- AM Molina, IF Avelino, EF Morales, LE Sucar, Causal Based Q-Learning, Research in Computing Science 149, 95-10, 2020 [PDF]
- VR López, LE Sucar, FO Espina, Toward Knowledge Transfer for Learning Markov Equivalence Classes, Research in Computing Science 149, 113-121, 2020 [PDF]
- MG Soto, LE Sucar, HJ Escalante, Causal Games and Causal Nash Equilibrium, Research in Computing Science 149, 123-133, 2020 [PDF]
- Verónica Rodríguez, L. Enrique Sucar. Felipe Orihuela-Espiona, Knowledge Transfer for Learning Subject-Specific Causal Probabilistic Graphical Models, Technical Report, INAOE, Nov 2019. [PDF]
- Mauricio González, L. Enrique Sucar, Hugo J. Escalantre, Causal Games and Causal Nash Equilibrium, arXiv, 2019 [PDF]
- Samuel
Montero-Hernandez, Felipe Orihuela-Espina, Luis Enrique Sucar, Paola
Pinti, Antonia Hamilton, Paul Burgess, Ilias Tachtsidis, Estimating Functional Connectivity Symmetry between Oxy- and Deoxy- Haemoglobin: Implications for fNIRS Connectivity Analysis, Algorithms, 11 (5), 2018. [MDPI]
- Samuel Montero-Hernandez, Felipe Orihuela-Espina, Luis Enrique Sucar, Intervals of Causal Effects for Learning Causal Graphical Models, International Conference on Probabilistic Graphical Models, pp. 296–307, JMLR Proceedings, 2018. [PMLR]
- Mauricio González-Soto, Luis Enrique Sucar, Hugo Jair Escalante, Playing against Nature: causal discovery for decision making under uncertainty, CausalML Workshop at ICML 2018. [arXiv]
- Samuel Antonio Montero-Hernandez, Felipe Orihuela-Espina, Javier Herrera-Vega, Luis Enrique Sucar, Causal Probabilistic Graphical Models for Decoding Effective Connectivity in Functional Near InfraRed Spectroscopy, FLAIRS 2016 [AAAI]
Lectures:
Course on Causal Graphical Models
Software:
Python Library for Probabilistic Graphical Models [GitHub]
Associated publication: Jonathan Serrano-Pérez, L. Enrique Sucar, PGM_PyLib: A Toolkit for Probabilistic Graphical Models in Python, Proceedings of the 10th International Conference on Probabilistic Graphical Models, PMLR 138:625-628, 2020. [PMLR]
Seminar Presentations:
2020
Schema Networks (Arquímides Méndez)
Maximal Ancestral Graphs (Sebastián Bejos)
Videos:
Jonas Peters, Causality
Bob Trenwith, Causality - Learning Causal Effects from Data
Chaochao Lu, Causal Reinforcement Learning
