no code implementations • 11 Mar 2024 • Kedar Karhadkar, Erin George, Michael Murray, Guido Montúfar, Deanna Needell
The problem of benign overfitting asks whether it is possible for a model to perfectly fit noisy training data and still generalize well.
no code implementations • 23 May 2023 • Erin George, Joyce Chew, Deanna Needell
To evaluate this method, we perform a series of common tests and demonstrate that measures of bias in the word embeddings are reduced in exchange for minor reduction in the semantic quality of the embeddings.
no code implementations • 7 Jan 2021 • Tamás Darvas, Erin George, Kevin Smith
We obtain sharp inequalities between the large scale asymptotic of the $J$ functional with respect to the $d_1$ metric on the space of Kahler metrics.
Differential Geometry Complex Variables