2 papers
cs.LG2026
Gradient-Discrepancy Acquisition for Pool-Based Active Learning
Mohamadsadegh Khosravani, Sandra Zilles
The effectiveness of active learning hinges on the choice of the acquisition criterion by which a learning algorithm selects potentially informative data points whose label is subs…
cs.LG2026
Selective Prediction from Agreement: A Lipschitz-Consistent Version Space Approach
Mohamadsadegh Khosravani
We consider selective classification with abstention in the fixed-pool (or transductive) setting, where the unlabeled pool is given beforehand and only a subset of points can be qu…