Alexandre Drouin

Fundamental Research Scientist

Element AI


I am a Fundamental Research Scientist at Element AI in Montreal, Canada and an Adjunct Professor of Computer Science at Laval University. My current research is at the intersection of causal inference and machine learning. I am particularly interested in methods for causal discovery, which I believe is a problem of fundamental interest in science.

I obtained my PhD in machine learning from Laval University, under the supervision of François Laviolette, Mario Marchand, and Jacques Corbeil. In my thesis, I proposed machine learning algorithms with theoretical guarantees to uncover genotype-to-phenotype associations in large genomic datasets, and showed how these could be used in addressing the global problem of antibiotic resistance.


  • Artificial Intelligence
  • Machine Learning
  • Causal Inference
  • Computational Biology


  • PhD in Artificial Intelligence, 2019

    Laval University

  • MSc in Artificial Intelligence, 2014

    Laval University

  • BSc in Computer Science, 2012

    Laval University


Quickly discover relevant content by filtering publications.
(2020). Synbols: Probing Learning Algorithms with Synthetic Datasets. Neural Information Processing Systems (NeurIPS 2020).

PDF Code

(2020). Differentiable Causal Discovery from Interventional Data. Neural Information Processing Systems (NeurIPS 2020).

PDF Code

(2020). Gradient-based Neural DAG Learning with Interventions. Causal Learning for Decision Making workshop, ICLR 2020.


(2020). Embedding Propagation: Smoother Manifold for Few-Shot Classification. European Conference on Computer Vision (ECCV 2020).

PDF Code

(2019). Deep learning for electromyographic hand gesture signal classification using transfer learning. IEEE Transactions on Neural Systems and Rehabilitation Engineering.

PDF Code

(2019). Interpretable genotype-to-phenotype classifiers with performance guarantees. Scientific reports.

PDF Code

(2017). Maximum margin interval trees. Neural Information Processing Systems (NIPS 2017).

PDF Code


Differentiable Causal Discovery with Observational and Interventional Data

Knowledge of the causal structure that underlies a data generating process is essential to answering questions of causal nature. Such …

La recherche en intelligence artificielle

Genotype-to-phenotype prediction of antimicrobial resistance

Machine learning for antibiotic resistance: from rule-based models to deep architectures

Maximum Margin Interval Trees