Gauthier Gidel
Appointment
Canada CIFAR AI Chair
Pan-Canadian AI Strategy
About
Appointed Canada CIFAR AI Chair – 2020
Gauthier Gidel is a Canada CIFAR AI Chair, a core member of Mila and an assistant professor at the Department of Computer Science and Operations Research (DIRO) at Université de Montréal.
His research focuses on generative modeling and multi-objective learning, such as alignment or adversarial robustness . He’s well known for his work in variational inequality for learning including theoretical analyses of GANs and introducing the extragradient method to the deep learning community. Gauthier co-organized a popular series of workshops on smooth games during NeurIPS. He organized the first three iterations of the ICLR blog post track.
Awards
- Borealis AI Graduate Fellowship, 2019
- DIRO Excellence Grant, 2017 and 2018
Relevant Publications
- Bertrand, Q., Bose, A. J., Duplessis, A., Jiralerspong, M., & Gidel, G. (2023). On the stability of iterative retraining of generative models on their own data. to appear in ICLR 2024.
- Gorbunov, Eduard, Nicolas Loizou, and Gauthier Gidel. "Extragradient method: O (1/k) last-iterate convergence for monotone variational inequalities and connections with cocoercivity." International Conference on Artificial Intelligence and Statistics. PMLR, 2022.
- Jiralerspong, M., Bose A.J., Gemp, I., Qin, C., Bachrach, Y., & Gidel G. (2023). Feature Likelihood Score: Evaluating Generalization of Generative Models Using Samples. In Advances in Neural Information Processing Systems
- Bubeck, S., Cherapanamjeri, Y., Gidel, G., & Tachet des Combes, R. (2021). A single gradient step finds adversarial examples on random two-layers neural networks. Advances in Neural Information Processing Systems 34(pp. 10081-10091).
Bose, A. J., Gidel, G., Berrard, H., Cianflone, A., Vincent, P., Lacoste-Julien, S., & Hamilton, W. L. (2020). Adversarial Example Games.
Czarnecki, W. M., Gidel, G., Tracey, B., Tuyls, K., Omidshafiei, S., Balduzzi, D., & Jaderberg, M. (2020). Real World Games Look Like Spinning Tops.