Sandra Zilles
Appointment
Canada CIFAR AI Chair
Pan-Canadian AI Strategy
About
Appointed Canada CIFAR AI Chair – 2021
Sandra Zilles is a Canada CIFAR AI Chair at Amii, a professor in the Department of Computer Science at the University of Regina, and a Canada Research Chair in Computational Learning Theory.
Zilles and her research team focus on theoretical aspects of machine learning. She is interested in methods for modelling and exploiting special types of interaction with machines to enable them to learn using less data than conventional approaches. She is working on several challenges: the interplay between data-efficient teaching and avoiding collusion; on trust in multi-agent systems; developing algorithms for aggregating the preferences of various entities in a system; and, learning succinct representations of structured textual data (such as DNA sequences, bibliography entries, and computer programs).
Awards
- Faculty of Science Excellence of Research Award, Faculty of Science, University of Regina, 2023
- Canada Research Chair (Tier 1) in Computational Learning Theory, NSERC, 2022
- Membership in the College of New Scholars, Artists, and Scientists of the Royal Society of Canada, 2017 - 2024
- NSERC Canada Research Chair (Tier 2) in Computational Learning Theory, 2010 - 2017 and 2017 - 2022
- CACS/AIC (Canadian Association for Computer Science) Outstanding Young Researcher Award, 2013
Relevant Publications
- Ali, A. M. H., Yang, B., & Zilles, S. (2024). Approximation algorithms for preference aggregation using CP-nets. Proceedings of the AAAI Conference on Artificial Intelligence, 38(9), 10433–10441.
- Fallat, S., Kirkpatrick, D., Simon, H. U., Soltani, A., & Zilles, S. (2023). On batch teaching without collusion. Journal of Machine Learning Research, 40, 1–33.
- Mansouri, F., Simon, H. U., Singla, A., & Zilles, S. (2022). On Batch Teaching with Sample Complexity Bounded by VCD. Advances in Neural Information Processing (NeurIPS).
- Nikravan, M. H., Movahedan, M., & Zilles, S. (2021). Precision-based boosting. Proceedings of the AAAI Conference on Artificial Intelligence, 35(10), 9153–9160.
Alanazi, E., Mouhoub, M., & Zilles, S. (2020). The complexity of exact learning of acyclic conditional preference networks from swap examples. Artificial Intelligence, 278, 103182.