Publications

(2022). Strong inductive biases provably prevent harmless interpolation. Preprint (to appear at ICLR 2023).

PDF Cite Code

(2021). Interpolation can hurt robust generalization even when there is no noise. In NeurIPS 2021.

PDF Cite Code Poster

(2021). Surprising benefits of ridge regularization for noiseless regression. In ICML 2021 Workshop OPPO.

PDF Cite Code

(2021). Maximizing the robust margin provably overfits on noiseless data. In ICML 2021 Workshop AML.

PDF Cite Code