My research interests revolve around fundamentally understanding and improving robustness, fairness, and more general reliability of modern machine leaning methods—especially in practically relevant contexts.
I recently finished a research internship in the Statistical Machine Learning group of Prof. Fanny Yang at the ETH Zurich Department of Computer Science, and am currently looking for a PhD position.
MSc in Computer Science, 2022
BSc in Computer Science, 2017
We show that the strength of a model’s inductive bias determines whether interpolation of noisy data is harmless or harmful.
We reveal unexpected benefits of regularization even in the overparameterized regime by proving that for both linear regression and classification, avoiding interpolation significantly improves generalization.