Author

Berk Ustun

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Jul 2025

Observational Multiplicity

A measure of regret is introduced for probabilistic classification tasks, which measures how the predictions of a model could change as a result of different training labels, and is used to show that regret is often higher for certain groups in the dataset and discuss potential applications of regret.

Erin George, Deanna Needell, Berk Ustun · arXiv.org · 2 citations · ⚡2