Jason Hartford

Currently a postdoc at Mila with Yoshua Bengio. Previously - PhD at UBC with Kevin Leyton-Brown.

prof_pic.jpg

I am broadly interested in how we can leverage structural assumptions about data generating processes to make flexible machine learning models generalize beyond the observed distribution of training data. To this end, I have worked on using deep learning for causal inference, and on designing deep network architectures for permutation invariant data. Since starting at Mila, I’ve been focusing on learning representations with identifiability guarantees.

selected publications

  1. Weakly Supervised Representation Learning with Sparse Perturbations
    Ahuja, Kartik,  Hartford, Jason,  and Bengio, Yoshua
    ; 2022
  2. Properties from mechanisms: an equivariance perspective on identifiable representation learning
    Ahuja, Kartik,  Hartford, Jason,  and Bengio, Yoshua
    In International Conference on Learning Representations ; (joint first author), spotlight presentation; 2022
  3. Valid Causal Inference with (Some) Invalid Instruments
    Hartford, Jason, Veitch, Victor,  Sridhar, Dhanya and 1 more author
    In Proceedings of the 38th International Conference on Machine Learning 18–24 jul 2021
  4. Deep IV: A Flexible Approach for Counterfactual Prediction
    Hartford, Jason, Lewis, Greg,  Leyton-Brown, Kevin and 1 more author
    In Proceedings of the 34th International Conference on Machine Learning 06–11 aug 2017