Skip to content
conftrace_
2026 AISTATS AISTATS 2026

On the Calibration of Survival Models with Competing Risks

Survival analysis deals with modeling the time until an event occurs, and accurate probability estimates are crucial for decision-making, particularly in the competing-risks setting where multiple events are possible. While recent work has addressed calibration in standard survival analysis, the competing-risks setting remains under-explored as it is harder (the calibration applies to both probabilities across classes and time horizon). We show that existing calibration measures are not suited to the competing-risk setting and that recent models do not give well-behaved probabilities. To address this, we introduce a dedicated framework with two novel calibration measures that are minimized for oracle estimators (i.e., both measures are proper). We also introduce some methods to estimate, test, and correct the calibration. Our recalibration methods yield better probabilities while preserving discrimination.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Data Science & Analytics and Healthcare & Medicine

More from AISTATS 2026

All AISTATS 2026 papers →