Sharp Class-Count Bounds for Calibration Reuse in Temperature-Scaled Conformal Prediction
Year: 2026
Type: preprint
Abstract: How much coverage can a conformal classifier lose when it uses the same observations to select a temperature and calibrate its prediction sets? For nonrandomized least-ambiguous classification with a fixed K-class softmax model, the temperature-and-threshold family has growth function at most m + 1 + (K − 2)m(m − 1) and VC dimension asymptotic to log₂ K. One fixed classifier can realize K − 1 independent score coordinates at prescribed temperatures. This gives an exact beta order-statistic law for the coverage of an adversarial calibration-only selector. At interior finite-rank coverage levels, the worst-selector marginal deficit has order min{1, √(log K / n)}, where n is the calibration sample size. The lower construction allows bounded logits and temperatures in any nonempty open interval of positive values. A three-class example compares adversarial selection with likelihood tuning. The results characterize worst-case calibration reuse for unmodified LAC sets.
Author: Mamun, S M Abdulla Al
Institution: University of Manchester
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7236607680
