Ph.D. Candidate in the David R. Cheriton School of Computer Science at the University of Waterloo. Affiliated with the Artificial Intelligence Group and supervised by Kate Larson.


I explore connections between social choice and machine learning.

Currently I am exploring how (and whether!) machine learning can be useful for learning about voting rules. I’m particularly focused on what ML models can teach us about existing rules and how they can be used to create new rules.

I have also spent a fair amount of time investigating potential uses for liquid democracy and viscous democracy. This has included considering whether delegation can be used to improve the performance of classifier ensembles in machine learning and uncovering in what settings delegative voting is most accurate.

I expect to finish my PhD in mid-late 2024 and am interested in your (academic or industry) job opportunities!


May 08, 2024 I will be at AAMAS in New Zealand with an extended abstract, 2 workshop papers, and to run the SCaLA workshop (it will be a busy week 😅).
May 07, 2024 AAMAS has accepted my proposal to run a brand-new workshop on “Social Choice and Learning Algorithms” with Roy Fairstein, Nick Mattei, and Zoi Terzopoulou. Interested in ML or social choice? Join us on May 7th if you are attending AAMAS!
Jul 17, 2023 I will be attending the COMSOC Summer School in Amsterdam. Come talk to me about my research 😀
Jul 23, 2022 Shiri Alouf-Heffetz and I have a long paper at IJCAI. Read it here and get in touch to chat about it!

selected publications

  1. How Should We Vote? A Comparison of Voting Systems within Social Networks
    Shiri Alouf-Heffetz , Ben Armstrong, Kate Larson , and 1 more author
    In Proceedings of the 31st International Joint Conference on Artificial Intelligence , Jul 2022
  2. Liquid Democracy for Low-Cost Ensemble Pruning
    Ben Armstrong, and Kate Larson
    May 2024
    Extended Abstract. Full version available on ArXiV.