Toniann Pitassi
Appointment
Canada CIFAR AI Chair
Pan-Canadian AI Strategy
About
Toniann Pitassi is a Canada CIFAR AI Chair at the Vector Institute, and a professor in the department of computer science with a joint appointment in mathematics at the University of Toronto. She is also a Bell Canada Chair in Information Systems.
Pitassi’s primary research area is computational complexity, to understand which computational problems can be solved efficiently, and to develop the most efficient, least costly algorithms for such problems. Efficiency and cost is measured in terms of three computational resources: time, space, and randomness. Her research goal is to understand how much of these resources are required to solve important computational problems, and to understand the relationships and tradeoffs between the resources. The most famous problem in the area, the P versus NP problem, is the driving force behind much of her research. Her work also focuses on fairness in artificial intelligence and how to address biased data sources.
Awards
- ACM Fellow, 2019
- Institute for Advanced Study (Princeton) Long-term member (5 years, 2017-22)
- European Association of Theoretical Computer Science Dissertation Award to her students, (2015, 2017)
- ACM Best Article, 2015
Relevant Publications
Madras, D., Creager, E., Pitassi, T., & Zemel, R. (2019). Fairness through causal awareness: Learning causal latent-variable models for biased data. In Proceedings of the conference on fairness, accountability, and transparency (pp. 349-358).
Dwork, C., Hardt, M., Pitassi, T., Reingold, O., & Zemel, R. (2012). Fairness through awareness. In Proceedings of the 3rd innovations in theoretical computer science conference (pp. 214-226).
Dwork, C., Naor, M., Pitassi, T., & Rothblum, G. N. (2010). Differential privacy under continual observation. In Proceedings of the forty-second ACM symposium on Theory of computing (pp. 715-724).
Beame, P., & Pitassi, T. (2001). Propositional Proof complexity: Past, Present. Future, 42-70.
Pitassi, T., Beame, P., & Impagliazzo, R. (1993). Exponential lower bounds for the pigeonhole principle. Computational complexity, 3(2), 97-140.
Support Us
CIFAR is a registered charitable organization supported by the governments of Canada, Alberta and Quebec, as well as foundations, individuals, corporations and Canadian and international partner organizations.