← Search

Jay Nandy

2 accepted papers

2024

Fairness under Covariate Shift: Improving Fairness-Accuracy Tradeoff with Few Unlabeled Test Samples

AAAI 2024technical

Covariate shift in the test data is a common practical phenomena that can significantly downgrade both the accuracy and the fairness performance of the model. Ensuring fairness across different sensitive groups under covariate shift is of paramount importance due to societal implications like crimin…

2020

Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution Examples

NeurIPS 2020poster

Among existing uncertainty estimation approaches, Dirichlet Prior Network (DPN) distinctly models different predictive uncertainty types. However, for in-domain examples with high data uncertainties among multiple classes, even a DPN model often produces indistinguishable representations from the o…