Finite-Sample-Corrected Conformal Test Martingales for Wireless Link Adaptation

Peixuan Wu, George Koudouridis, Genghua Dong
Proceedings of the Fifteenth Symposium on Conformal and Probabilistic Prediction with Applications, PMLR 329:1053-1056, 2026.

Abstract

Conformal test martingales (CTMs) bet on conformal p-values to accumulate evidence against exchangeability. With finite calibration, a threshold event has finite-grid uncertainty around its nominal probability. We use the Dvoretzky-Kiefer-Wolfowitz inequality to bound this probability and subtract the largest admissible positive excess expected gain. Under the stated continuous score null and a predictable betting schedule, the corrected single-score wealth is a nonnegative supermartingale on the calibration event. A simulated wireless replay illustrates how the corrected evidence process enters an online monitoring pipeline for alarms and retraining decisions.

Cite this Paper

BibTeX
@InProceedings{pmlr-v329-wu26a, title = {Finite-Sample-Corrected Conformal Test Martingales for Wireless Link Adaptation}, author = {Wu, Peixuan and Koudouridis, George and Dong, Genghua}, booktitle = {Proceedings of the Fifteenth Symposium on Conformal and Probabilistic Prediction with Applications}, pages = {1053--1056}, year = {2026}, editor = {Ahlberg, Ernst and Johansson, Ulf and Boström, Henrik and Carlevaro, Alberto and Hallberg Szabadváry, Johan and Carlsson, Lars}, volume = {329}, series = {Proceedings of Machine Learning Research}, month = {02--04 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v329/main/assets/wu26a/wu26a.pdf}, url = {https://proceedings.mlr.press/v329/wu26a.html}, abstract = {Conformal test martingales (CTMs) bet on conformal p-values to accumulate evidence against exchangeability. With finite calibration, a threshold event has finite-grid uncertainty around its nominal probability. We use the Dvoretzky-Kiefer-Wolfowitz inequality to bound this probability and subtract the largest admissible positive excess expected gain. Under the stated continuous score null and a predictable betting schedule, the corrected single-score wealth is a nonnegative supermartingale on the calibration event. A simulated wireless replay illustrates how the corrected evidence process enters an online monitoring pipeline for alarms and retraining decisions.} }
Endnote
%0 Conference Paper %T Finite-Sample-Corrected Conformal Test Martingales for Wireless Link Adaptation %A Peixuan Wu %A George Koudouridis %A Genghua Dong %B Proceedings of the Fifteenth Symposium on Conformal and Probabilistic Prediction with Applications %C Proceedings of Machine Learning Research %D 2026 %E Ernst Ahlberg %E Ulf Johansson %E Henrik Boström %E Alberto Carlevaro %E Johan Hallberg Szabadváry %E Lars Carlsson %F pmlr-v329-wu26a %I PMLR %P 1053--1056 %U https://proceedings.mlr.press/v329/wu26a.html %V 329 %X Conformal test martingales (CTMs) bet on conformal p-values to accumulate evidence against exchangeability. With finite calibration, a threshold event has finite-grid uncertainty around its nominal probability. We use the Dvoretzky-Kiefer-Wolfowitz inequality to bound this probability and subtract the largest admissible positive excess expected gain. Under the stated continuous score null and a predictable betting schedule, the corrected single-score wealth is a nonnegative supermartingale on the calibration event. A simulated wireless replay illustrates how the corrected evidence process enters an online monitoring pipeline for alarms and retraining decisions.
APA
Wu, P., Koudouridis, G. & Dong, G.. (2026). Finite-Sample-Corrected Conformal Test Martingales for Wireless Link Adaptation. Proceedings of the Fifteenth Symposium on Conformal and Probabilistic Prediction with Applications, in Proceedings of Machine Learning Research 329:1053-1056 Available from https://proceedings.mlr.press/v329/wu26a.html.

Related Material