Directory of Experts
Back to search results
Matthew Joseph Kusner
Ph.D. (WashU)

Research interests and affiliations

Research interests
  • Machine learning
  • Evaluation
  • Testing
  • Attacks
  • Defenses
  • Regulation
Expertise type(s) (NSERC subjects)
  • 2605 Pattern analysis and machine intelligence
  • 2713 Algorithms
  • 2805 Learning and inference theories

Publications

Recent publications
Conference paper
Alabdulmohsin, I., Chiou, N., D'Amour, A., Gretton, A., Koyejo, S., Kusner, M. J., Pfohl, S. R., Salaudeen, O., Schrouff, J., & Tsai, K. (2023, April). Adapting to latent subgroup shifts via concepts and proxies [Paper]. 26th International Conference on Artificial Intelligence and Statistics (AISTATS 2023), Palau de Congressos, Valencia, Spain. Published in Proceedings of Machine Learning Research, 206.
Conference paper
Kaddour, J., Liu, L., Silva, R., & Kusner, M. J. (2022, November). When Do Flat Minima Optimizers Work? [Paper]. 36th Conference on Neural Information Processing Systems (NeurIPS 2022), New Orleans, Louisiana (19 pages).

Biography

Matt Kusner is an Associate Professor at Polytechnique Montréal. He received his PhD in Computer Science from Washington University in St. Louis in 2016 under the supervision of Kilian Weinberger. His work was given the Turner Dissertation Award for best doctoral dissertation in Computer Science & Engineering. He was part of the first cohort of Research Fellows at the Alan Turing Institute in London, UK's National Institute for Data Science and Artificial Intelligence. He has given talks for the Federal Reserve Banks of Cleveland and Philadelphia, the Cambridge Centre for Mathematical Sciences, and the Royal Society. His work has appeared in the Guardian, Forbes, and the Harvard Business Review. Before joining Polytechnique Montréal, he was an Associate Professor at University College London, and earlier an Associate Professor at the University of Oxford and a Tutorial Fellow at Jesus College.