Pandora's Regret is a closed-form pairwise scoring rule derived from expected optimal search costs that elicits true probabilities and outperforms log loss, accuracy, and F1 at predicting diagnostic costs on MedMNIST models.
Chenze Shao, Fandong Meng, Yijin Liu, and Jie Zhou
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Perturbing prefixes to semantic neighbors during training creates a hierarchical noise model that improves language model predictions on token sequences outside the training corpus support.
A review summarizing mathematical foundations, characterization results, families of proper scoring rules, and their roles in statistics and machine learning for estimation and forecast evaluation.
citing papers explorer
-
Pandora's Regret: A Proper Scoring Rule for Evaluating Sequential Search
Pandora's Regret is a closed-form pairwise scoring rule derived from expected optimal search costs that elicits true probabilities and outperforms log loss, accuracy, and F1 at predicting diagnostic costs on MedMNIST models.
-
Perturbation is All You Need for Extrapolating Language Models
Perturbing prefixes to semantic neighbors during training creates a hierarchical noise model that improves language model predictions on token sequences outside the training corpus support.
-
Proper scoring rules for estimation and forecast evaluation
A review summarizing mathematical foundations, characterization results, families of proper scoring rules, and their roles in statistics and machine learning for estimation and forecast evaluation.