Elias Bareinboim
Elias Bareinboim develops causal methods for AI, studying how systems can reason about interventions, changing data sources and decisions. Bareinboim earned his doctorate at UCLA under Judea Pearl. His work connects causal inference with AI and data science, including the problem of making claims from biased or heterogeneous data and transferring them across settings. A shared ICML 2022 tutorial with Daniel Plecko addressed causal inference and fairness. His work also includes a 2024 Foundations and Trends in Machine Learning paper on causal fairness analysis, alongside work relating neural and causal reasoning.
- Now at
- Columbia University
- Works
- 137
- Citations
- 3,666
- h-index
- 29
Publication numbers from OpenAlex, as of 14 October 2026.
Timeline
-
Education and research foundations
Working on the foundations of causality
Bareinboim earned his doctorate at UCLA under Judea Pearl. His work connects causal inference with AI and data science, including the problem of making claims from biased or heterogeneous data and transferring them across settings.
-
2019
Identifiability across experiments
With Sanghack Lee and Juan Correa, he coauthored General Identifiability with Arbitrary Surrogate Experiments. The work received the UAI 2019 Best Paper Award.
-
2020
Causal reinforcement learning
He introduced the causal reinforcement-learning framework in an ICML 2020 tutorial. The research program studies how causal knowledge can inform learning and decision-making, with papers spanning several later conferences.
-
2022–2024
Fairness and causal models
A shared ICML 2022 tutorial with Daniel Plecko addressed causal inference and fairness. His work also includes a 2024 Foundations and Trends in Machine Learning paper on causal fairness analysis, alongside work relating neural and causal reasoning.
Sources and credits
Photo: causalai.net; creator not stated. License: Not stated by source. Source: causalai.net. Cropped to a square and resized. Ask us to remove or replace this photo.