Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Test-time augmentation improves efficiency in conformal prediction
Divya Shanmugam, Helen Lu, Swami Sankaranarayanan +1
A conformal classifier produces a set of predicted classes and provides a probabilistic guarantee that the set includes the true class. Unfortunately, it is often the case that con…
cs.LG2024
Efficient Bias Mitigation Without Privileged Information
Mateo Espinosa Zarlenga, Swami Sankaranarayanan, Jerone T. A. Andrews +3
Deep neural networks trained via empirical risk minimisation often exhibit significant performance disparities across groups, particularly when group and task labels are spuriously…