Research
Calibrating conditional risk
arXiv:2604.20409v1 Announce Type: new Abstract: We introduce and study the problem of calibrating conditional risk, which involves estimating the expected loss of a prediction model conditional on inp
arXiv:2604.20409v1 Announce Type: new Abstract: We introduce and study the problem of calibrating conditional risk, which involves estimating the expected loss of a prediction model conditional on input features. We analyze this problem in both classification and regression settings and show that it is fundamentally equivalent to a standard regression task. For classification settings, we further establish a connection between conditional risk calibration and individual/conditional probability calibration, and develop theoretical insights for the performance metric. This reveals that while conditional risk calibration is related to existing uncertainty quantification problems, it remains a distinct and standalone machine learning problem. Empirically, we validate our theoretical findings and demonstrate the practical implications of conditional risk calibration in the learning to defer (L2D) framework. Our systematic experiments provide both qualitative and quantitative assessments, offering guidance for future research in uncertainty-aware decision-making.
Related
- PAC-Bayesian Bounds on Constrained f-Entropic Risk Measures
- Expert-Guided Class-Conditional Goodness-of-Fit Scores for Interpretable Classification with Informative Missingness: An Application to Seismic Monitoring
- Wasserstein Distributionally Robust Risk-Sensitive Estimation via Conditional Value-at-Risk
- On Different Notions of Redundancy in Conditional-Independence-Based Discovery of Graphical Models
Source: arXiv cs.LG | 2026-04-23