Talks
From kernel methods to neural networks: double descent, function spaces, curse of dimensionality at University of Warwick (Statistics Seminar, 2024); University of Genoa (MaLGa Seminar, 2024)
Can we avoid robust overfitting in adversarial training? - An approximation viewpoint (regression part) at UW-Madison (MLOPT Idea Seminar, 2024)
The role of over-parameterisation in machine learning - the good, the bad, the ugly (from the function space perspective) at New Faculty Highlights, AAAI 2024
On the Convergence of Encoder-only Shallow Transformers at UBC (MILD Seminar 2024)
Robustness in deep learning: the good, the bad, the ugly at KAUST (Rising Stars in AI Symposium 2023)
Double descent of random features models trained with SGD at KU Leuven, 2022
Kernel approximation via random features and quadrature at UC Berkeley (on zoom), 2021