1 code implementation • 23 Jan 2024 • Andrea Pugnana, Lorenzo Perini, Jesse Davis, Salvatore Ruggieri
The selective classification framework aims to design a mechanism that balances the fraction of rejected predictions (i. e., the proportion of examples for which the model does not make a prediction) versus the improvement in predictive performance on the selected predictions.
no code implementations • 15 Nov 2023 • Andrea Pugnana, Carlos Mougan, Dan Saattrup Nielsen
Such a framework is known as selective prediction.
1 code implementation • 19 Oct 2022 • Andrea Pugnana, Salvatore Ruggieri
We propose a model-agnostic approach to associate a selection function to a given probabilistic binary classifier.