Jason Hartford

Dame Kathleen Ollerenshaw Fellow at the University of Manchester (starting October 2024), and Research Unit Lead / Staff Research Scientist at Valence Labs.

prof_pic.jpg

I work on building the tools to enable scientific discovery from complex, high-dimensional data. Most of my current research focuses on developing new techniques for causal representation learning and causal inference, as well as active learning techniques for designing experiments to learn causal models. Before starting at Valence and Manchester, I completed a post-doc with Yoshua Bengio at Université de Montréal, and before that, I completed my PhD at the University of British Columbia with Kevin Leyton-Brown.

selected publications

  1. Weakly Supervised Representation Learning with Sparse Perturbations
    Ahuja, Kartik,  Hartford, Jason,  and Bengio, Yoshua
    In Advances in Neural Information Processing Systems ; 2022
  2. Sequential Underspecified Instrument Selection for Cause-Effect Estimation
    Ailer, Elisabeth,  Hartford, Jason,  and Kilbertus, Niki
    In Proceedings of the 40th International Conference on Machine Learning ; oral presentation (2% acceptance); 2023
  3. 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 (5% acceptance); 2022
  4. 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
  5. 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