Paper ICML 2026 DBMS

Learned Cardinality with Distribution-Free Confidence

Jihoon Park, Aylin Demir, Sasha Volkov · OOAARG · Department of Computer Science

arXiv:2604.18221
OON · O(d log T) ONS · O(√T) R(T) T (rounds, ×10³)

Calibrated cardinality estimation under workload drift — confidence intervals that hold without distributional assumptions, with provable coverage. Our estimator wraps any black-box learned cardinality model with a calibration layer based on conformal prediction, giving distribution-free guarantees that survive arbitrary shifts in the query workload.