← Search

Drona Khurana

1 accepted papers

2025

Consistency Conditions for Differentiable Surrogate Losses

NeurIPS 2025poster

The statistical consistency of surrogate losses for discrete prediction tasks is often checked using the condition of calibration. However, directly verifying calibration can be arduous. Recent work shows that for polyhedral surrogates, a less arduous condition, indirect elicitation (IE), is still e…

Cited by 0SourceScholar