Jason Hartford

I am now a post-doc at Mila and have a new website here. This website is no longer actively maintained.

Contact:

Research

Valid Causal Inference with (Some) Invalid Instruments. Jason Hartford, Victor Veitch, Dhanya Sridhar, Kevin Leyton-Brown.

Exemplar guided active learning. Jason Hartford, Kevin Leyton-Brown, Hadas Raviv, Dan Padnos, Shahar Lev, Barak Lenz. NeurIPS 2020.

Identifying Valid Instruments via Effect Agreement. Jason Hartford, Kevin Leyton-Brown. “Do the right thing”: Machine Learning and Causal Inference for Improved Decision Making Workshop at NeurIPS, 2019.

Predicting Propositional Satisfiability via End-to-End Learning. Chris Cameron, Rex Chen, Jason Hartford, Kevin Leyton-Brown. AAAI 2020.

Predicting Propositional Satisfiability via End-to-End Learning. Chris Cameron, Rex Chen, Jason Hartford, Kevin Leyton-Brown. Graph Representation Learning Workshop at NeurIPS 2019 (superceded by AAAI 2020 paper).

Deep Models of Interactions Across Sets Jason Hartford, Devon R Graham, Kevin Leyton-Brown, Siamak Ravanbakhsh. ICML 2018.

Deep IV: A Flexible Approach for Counterfactual Prediction Jason Hartford, Greg Lewis, Kevin Leyton-Brown, Matt Taddy. ICML 2017. Code / Talk

Counterfactual Prediction with Deep Instrumental Variables Networks. Jason Hartford, Greg Lewis, Kevin Leyton-Brown, Matt Taddy What if? Inference and Learning of Hypothetical and Counterfactual Interventions in Complex Systems. NIPS Workshop, 2016

Deep Learning for Predicting Human Strategic Behavior. Jason Hartford, James R. Wright, Kevin Leyton-Brown. NIPS 2016 Oral Presentation. Code / Talk

Selected Employment

2017 - CPSC 540 Graduate Machine Learning TA.

2017 - Intern Microsoft Research.

2016 - Intern Microsoft Research.

2014 - 2015 UBC Graduate TA for the CSPC 340 machine learning course and CSPC 301 Computing for Life Sciences course.

2013 - 2014 Associate Lecturer - University of Witwatersrand lecturing Microeconomics and Econometrics.