I am currently a post-doc working on kernel methods and adversarial vulnerability.
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.