Bio

Antonin Schrab is a PhD student at University College London who is jointly supervised by Benjamin Guedj at the UCL Centre for Artificial Intelligence and Inria London, and by Arthur Gretton at the Gatsby Computational Neuroscience Unit. His research focuses on designing kernel-based hypothesis tests for the two-sample, independence and goodness-of-fit problems, with an equally strong emphasis on both theory (minimax optimality guarantees) and practicality (user-friendly parameter-free implementations). One common theme throughout his research is addressing the fundamental problem of kernel selection for kernel-based hypothesis tests, either via Aggregation, or via Fusion. He has also recently worked on constructing differentially private permutation tests.