Confounding-Valid Conformal Inference for Counterfactual KPIs in Wireless Networks

The paper introduces Confounding-Valid Counterfactual Conformal Inference (CV‑CCI), a method that merges abundant observational telemetry with limited randomized data to answer network operators’ ‘what‑if’ questions about key performance indicators (KPIs). CV‑CCI uses the General Synthetic‑Powered Inference principle to maintain finite‑sample coverage guarantees even when hidden confounding is present, while producing tighter prediction sets than existing baselines. Experiments on two radio access network control tasks demonstrate the method’s validity under hidden confounding and its improved efficiency.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

• benchmarks