Elias Bareinboim


      CausalAI Lab
       Department of Computer Science
       Department of Statistics (by courtesy)
      Purdue University

      Web: causalai.net
      Email: eb at purdue dot edu
      Twitter: @eliasbareinboim
      Address: 305 N. University Street 2142L
      West Lafayette, IN, 47907-2107.





summarynewsteachingservicetutorialstalkspublications ]

Summary

I obtained my Ph.D. from the Computer Science Department at UCLA, advised by Judea Pearl. My research focuses on causal inference and its applications to bioinformatics, economics, medicine, and public health (which has recently been called data science).

More specifically, my research is concerned with the robustness and generalizability of causal and counterfactual claims in the context of heterogeneous and biased data collections, including due to issues of confounding bias, selection bias, and external validity. A recent summary of this work, when combining massive sets of research data, appeared at the Proceedings of the National Academy of Sciences (PNAS), see the
story and the paper. A brief summary of the automated scientist project was also highlighted at the IEEE Intelligent Systems (link, story). More recently, I have been exploring the intersection of causality with reinforcement learning (NIPS-15, ICML-17, IJCAI-17) and fairness analysis (AAAI-18).

I am broadly interested in Artificial Intelligence, Machine Learning, Statistics, Robotics, Cognitive Science, and Philosophy of Science.

My CV: pdf (Sep/6, 2018)

News

Teaching

Academic Service

Tutorials

Invited talks



Publications

2018:

Equality of Opportunity in Classification: A Causal Approach
J. Zhang, E. Bareinboim
NIPS-18. In Proceedings of the 32nd Annual Conference on Neural Information Processing Systems, 2018.
Purdue CausalAI Lab, Technical Report (R-37), 2018, forthcoming.

Structural Causal Bandits: Where to Intervene?
S. Lee, E. Bareinboim
NIPS-18. In Proceedings of the 32nd Annual Conference on Neural Information Processing Systems, 2018.
Purdue CausalAI Lab, Technical Report (R-36), 2018, forthcoming.

Causal Identification under Markov Equivalence
A. Jaber, JJ. Zhang, E. Bareinboim
UAI-18. In Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence, 2018.
Purdue CausalAI Lab, Technical Report (R-35), August, 2018. [
pdf]

Best Student Paper Award (1 out of 337 papers).

Non-Parametric Path Analysis in Structural Causal Models
J. Zhang, E. Bareinboim
UAI-18. In Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence, 2018.
Purdue CausalAI Lab, Technical Report (R-34), May, 2018. [pdf]

Budgeted Experimental Design for Causal Structural Learning
A. Ghassami, S. Salehkaleybar, N. Kiyavash, E. Bareinboim
ICML-18. In Proceedings of the 34th International Conference on Machine Learning, 2018.
Purdue CausalAI Lab, Technical Report (R-33), May, 2018. [pdf]

A Graphical Criterion for Effect Identification in Equivalence Classes of Causal Diagrams
A. Jaber, JJ. Zhang, E. Bareinboim.
IJCAI-18. In Proceedings of the 26th International Joint Conference on Artificial Intelligence, 2018.
Purdue CausalAI Lab, Technical Report (R-32), May, 2018. [pdf]

A note on "Generalizability of Study Results (Lesko et al., 2017)"
J. Pearl, E. Bareinboim.
EPI-18. Epidemiology, 2018, forthcoming.
Purdue CausalAI Lab, Technical Report (R-31), Apr, 2018. [pdf]

Fairness in Decision-Making -- The Causal Explanation Formula
J. Zhang, E. Bareinboim.
AAAI-18. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence, 2018.
Purdue CausalAI Lab, Technical Report (R-30), Nov, 2017. [pdf]

Generalized Adjustment Under Confounding and Selection Biases
J. Correa, J. Tian, E. Bareinboim.
AAAI-18. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence, 2018.
Purdue CausalAI Lab, Technical Report (R-29), Nov, 2017. [pdf]

Outstanding Paper Award Honorable Mention (2 out of 3800 papers).

2017:

Experimental Design for Learning Causal Graphs with Latent Variables
M. Kocaoglu, K. Shanmugam, E. Bareinboim.
NIPS-17. In Proceedings of the 31st Annual Conference on Neural Information Processing Systems, 2017.
Purdue CausalAI Lab, Technical Report (R-28), Nov, 2017. [pdf]

Identification and Model Testing in Linear Structural Equation Models using Auxiliary Variables
B. Chen, D. Kumor, E. Bareinboim.
ICML-17. In Proceedings of the 34th International Conference on Machine Learning, 2017.
Purdue CausalAI Lab, Technical Report (R-27), Jun, 2017. [pdf]

Counterfactual Data-Fusion for Online Reinforcement Learners
A. Forney, J. Pearl, E. Bareinboim.
ICML-17. In Proceedings of the 34th International Conference on Machine Learning, 2017.
Purdue CausalAI Lab, Technical Report (R-26), Jun, 2017. [pdf]

Transfer Learning in Multi-Armed Bandits: A Causal Approach
J. Zhang, E. Bareinboim.
IJCAI-17. In Proceedings of the 26th International Joint Conference on Artificial Intelligence, 2017.
Purdue CausalAI Lab, Technical Report (R-25), Jun, 2017. [pdf]

Causal Effect Identification by Adjustment under Confounding and Selection Biases
J. Correa, E. Bareinboim.
AAAI-17. In Proceedings of the 31st AAAI Conference on Artificial Intelligence, 2017.
Purdue CausalAI Lab, Technical Report (R-24), Nov, 2016. [pdf]

2016:

Causal inference and the data-fusion problem
E. Bareinboim, J. Pearl.
PNAS-16. Proceedings of the National Academy of Sciences, v. 113 (27), pp. 7345-7352, 2016. [pdf]

Identification by Auxiliary Instrumental Sets in Linear Structural Equation Models
B. Chen, J. Pearl, E. Bareinboim.
IJCAI-16. In Proceedings of the 25th International Joint Conference on Artificial Intelligence, 2016. [pdf]

Comment on "Causal Inference using invariance prediction: identification and confidence intervals (by Peters, Buhlmann and Meinshausen)"
E. Bareinboim.
RSS-16. Journal of the Royal Statistical Society, Series B, forthcoming.

Markov Decision Processes with Unobserved Confounders: A Causal Approach
J. Zhang, E. Bareinboim.
Purdue CausalAI Lab, Technical Report (R-23), 2016. [pdf]

2015:

Bandits with Unobserved Confounders: A Causal Approach
E. Bareinboim, A. Forney, J. Pearl.
NIPS-15. In Proceedings of the 28th Annual Conference on Neural Information Processing Systems, 2015. [pdf]

Recovering Causal Effects From Selection Bias
E. Bareinboim, J. Tian.
AAAI-15. In Proceedings of the 29th AAAI Conference on Artificial Intelligence, 2015. [pdf]

2014:

Transportability from Multiple Environments with Limited Experiments: Completeness Results
E. Bareinboim, J. Pearl.
NIPS-14. In Proceedings of the 27th Annual Conference on Neural Information Processing Systems, 2014. [pdf]
Spotlight Presentation (62 out of 1678 papers).

Recovering from Selection Bias in Causal and Statistical Inference
E. Bareinboim, J. Tian, J. Pearl.
AAAI-14. In Proceedings of the 28th AAAI Conference on Artificial Intelligence, 2014. [pdf]
Supplemental material, UCLA Cognitive Systems Laboratory, Technical Report (R-425-sup). [pdf]

Best Paper Award (1 out of 1406 papers).

External Validity: From do-calculus to Transportability across Populations
J. Pearl, E. Bareinboim.
StSci-14. Statistical Science, v. 29(4), pp. 579-595, 2014. [pdf]

Generalizability in Causal Inference: Theory and Algorithms
E. Bareinboim.
Ph.D. Thesis, Computer Science Department, UCLA, 2014.

2013:

Causal Transportability from Multiple Environments with Limited Experiments
E. Bareinboim, S. Lee, V. Honavar, J. Pearl.
NIPS-13. In Proceedings of the 26th Annual Conference on Neural Information Processing Systems, 2013. [pdf]

Causal Transportability with Limited Experiments
E. Bareinboim, J. Pearl.
AAAI-13. In Proceedings of the 27th AAAI Conference on Artificial Intelligence, 2013. [pdf]

Meta-Transportability of Causal Effects: A formal approach
E. Bareinboim, J. Pearl.
AISTATS-13. In Proceedings of the 16th International Conference on Artificial Intelligence and Statistics, 2013. [pdf]

A General Algorithm for Deciding Transportability of Experimental Results
E. Bareinboim, J. Pearl.
JCI-13. Journal of Causal Inference, v. 1(1), pp. 107--134, 2013. [pdf]

2012:

Causal Inference by Surrogate Experiments
E. Bareinboim, J. Pearl.
UAI-12. In Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence, 2012. [pdf]

Transportability of Causal Effects: Completeness Results
E. Bareinboim, J. Pearl.
AAAI-12. In Proceedings of the 26th AAAI Conference on Artificial Intelligence, 2012. [pdf]

Controlling Selection Bias in Causal Inference
E. Bareinboim, J. Pearl.
AISTATS-12. In Proceedings of the 15th International Conference on Artificial Intelligence and Statistics, 2012. [pdf]

Local Characterizations of Causal Bayesian Networks
E. Bareinboim, C. Brito, J. Pearl.
LNAI-12. In Lecture Notes in Artificial Intelligence, Springer, 2012. [pdf]

2011:

Transportability of Causal and Statistical relations: A formal approach
J. Pearl, E. Bareinboim.
AAAI-11. In Proceedings of the 25th AAAI Conference on Artificial Intelligence, 2011. [pdf]
Extended Technical Report (R-372), UCLA Cognitive Systems Laboratory. [pdf]

Controlling Selection Bias in Causal Inference (Short paper)
E. Bareinboim, J. Pearl.
AAAI-11. In Proceedings of the 25th AAAI Conference on Artificial Intelligence, 2011. [pdf]

External Validity and Transportability: A Formal Approach
J. Pearl, E. Bareinboim.
JSM-ASA-11. In Proceedings of the Joint Statistical Meetings, American Statistical Association, 2011. [pdf]

Local Characterizations of Causal Bayesian Networks
E. Bareinboim, C. Brito, J. Pearl.
GKR-IJCAI-11. In Proceedings of the GKR-22nd International Joint Conference on Artificial Intelligence, 2011. [pdf]

Analyzing marginal cases in differential shotgun proteomics
P. Carvalho, J. Fischer, J. Perales, J. Yates III, V. Barbosa, E. Bareinboim.
Bioinformatics, Vol 27, pp. 275-276, 2011. [pdf]

Pre-PhD:

Descents and nodal load in scale-free networks
E. Bareinboim, V.C. Barbosa.
Physical Review E, Vol. 77, 046111, 2008. [pdf]


September 7, 2018.