4 papers
Margin Certificates for Voting Classifiers under Mixing Dependence
Adria Binte Habib, Ibne Farabi Shihab
Margin bounds explain why weighted votes generalize after training error vanishes, but dependent observations require concentration arguments that keep the dependence model and fai…
Selection-Safe Conformal Early Exit: Distribution-Free Coverage under Adaptive Depth
Adria Binte Habib, Ibne Farabi Shihab
Calibrating a conformal prediction set at each early exit does not preserve coverage once a data-dependent exit is selected. We construct one terminal path score from prefix maxima…
Candidate-Label Saliency for Efficient Conformal Pruning of Text Classifiers
Ibne Farabi Shihab, Adria Binte Habib, Anuj Sharma +1
Recalibration can preserve conformal coverage after pruning while enlarging prediction sets and leaving more alternatives for downstream decisions. Directly searching for deletions…
The Cost of Adaptivity: Matching Lower Bounds Across Learning Problems
Ibne Farabi Shihab, Adria Binte Habib
Adaptive procedures must work without nuisance information an oracle may use, such as a gradient scale or smoothness index, and robust procedures may have to answer queries whose c…