On August 1, 2019, I started a post-doc in the Learning and Adaptive Systems group at the ETH Zürich.
I am currently a post-doc working on kernel methods and adversarial vulnerability. I completed my PhD in the causal learning and learning theory group of the Empirical Inference department and was graciously supported by a Google European Doctoral Fellowship.
My research focuses mainly on kernel methods, such as kernel mean embeddings. They lead to metrics over distributions, which are now widely used to design distribution comparison tests, such as the Maximum Mean Discrepancy and the HSIC test. Studying these metrics, I have also turned towards generative adversarial nets (GANs), which can be seen as another way to define and minimize a useful distance between two empirical distributions. Finally, I recently turned towards understanding adversarial vulnerability, where it comes from, and what can be done to tackle it.
Aug.19 - Present: Post-Doc at the Learning and Adaptive Systems group, ETH Zürich
Jan. 19 - Jul. 19: Post-Doc at the Max-Planck-Institute for Intelligent Systems
Sept. 13 - Dec. 18: PhD Student at the Max Planck Institute for Intelligent Systems (supported in part by the Google Doctoral European Fellowship in Causal Inference)
July 2013 : General Engineering Master Diploma at Mines ParisTech (Ecole Nationale Supérieure des Mines de Paris), Major: Geostatistics
Proceedings of the 36th International Conference on Machine Learning (ICML), 97, pages: 5809-5817, Proceedings of Machine Learning Research, (Editors: Chaudhuri, Kamalika and Salakhutdinov, Ruslan), PMLR, June 2019 (conference)
Advances in Neural Information Processing Systems 30, pages: 5424-5433, (Editors: Guyon I. and Luxburg U.v. and Bengio S. and Wallach H. and Fergus R. and Vishwanathan S. and Garnett R.), Curran Associates, Inc., 31st Annual Conference on Neural Information Processing Systems, December 2017 (conference)
Tolstikhin, I., Gelly, S., Bousquet, O., Simon-Gabriel, C. J., Schölkopf, B.AdaGAN: Boosting Generative ModelsAdvances in Neural Information Processing Systems 30, pages: 5424-5433, (Editors: Guyon I. and Luxburg U.v. and Bengio S. and Wallach H. and Fergus R. and Vishwanathan S. and Garnett R.), Curran Associates, Inc., 31st Annual Conference on Neural Information Processing Systems, December 2017 (conference)
Advances in Neural Information Processing Systems 29, pages: 1732-1740, (Editors: D. D. Lee, M. Sugiyama, U. V. Luxburg, I. Guyon, and R. Garnett), Curran Associates, Inc., 30th Annual Conference on Neural Information Processing Systems, December 2016, *joint first authors (conference)
In Proceedings of The 32nd International Conference on Machine Learning, 37, pages: 2218–2226, JMLR Workshop and Conference Proceedings, (Editors: Bach, F. and Blei, D.), JMLR, ICML, 2015 (inproceedings)
Our goal is to understand the principles of Perception, Action and Learning in autonomous systems that successfully interact with complex environments and to use this understanding to design future systems