Shai Ben-David
Appointment
Canada CIFAR AI Chair
Pan-Canadian AI Strategy
About
Appointed Canada CIFAR AI Chair – 2018
Shai Ben-David is a Canada CIFAR AI Chair at the Vector Institute and a professor at the Cheriton School of Computer Science at the University of Waterloo.
Ben-David’s research interests span a range of topics in computer science theory with a focus on machine learning. Among his notable contributions in that field are pioneering steps in the analysis of domain adaptation, unsupervised learning, including clustering and density estimation, and change detection in streaming data.
Awards
- Named ACM Fellow, 2024
- Best Paper Award, Algorithmic Learning Theory Conference, 2023
- Research Chair, University of Waterloo, 2020
- Best Paper Award, NeurIPS, 2018
- Best Student Paper Award, COLT, 2011
- Best Student Paper Award, COLT, 2006
- Best Student Paper Award, ICASSP, 2005
Relevant Publications
H Ashtiani, S Ben-David, NJA Harvey, C Liaw, A Mehrabian, Y Plan (2020). Near-optimal sample complexity bounds for robust learning of gaussian mixtures via compression schemes. Journal of the ACM (JACM) 67 (6), 1-42.
Ben-David, S., Hrubeš, P., Moran, S., Shpilka, A., Yehudayoff A. (2019). Learnability can be undecidable. Nature Machine Intelligence 1 (1), 44
Donini, M., Oneto, L., Ben-David, S., Shawe-Taylor, J., & Pontil, M. (2018). Empirical risk minimization under fairness constraints.
Shalev-Shwartz, S., & Ben-David, S. (2014). Understanding machine learning: From theory to algorithms. Cambridge university press.
Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., & Vaughan, J. W. (2010). A theory of learning from different domains. Machine learning, 79(1), 151-175.
Ben-David, S., Blitzer, J., Crammer, K., & Pereira, F. (2007). Analysis of representations for domain adaptation. Advances in neural information processing systems, 19, 137.
Kifer, D., Ben-David, S., & Gehrke, J. (2004). Detecting change in data streams. In VLDB (Vol. 4, pp. 180-191).