Adaptive Conformal Prediction for 5G Link Adaptation under Distribution Shift

Emanuele Minotti, Genghua Dong, George Koudouridis
Proceedings of the Fifteenth Symposium on Conformal and Probabilistic Prediction with Applications, PMLR 329:1049-1052, 2026.

Abstract

In 5G link adaptation a modulation and coding scheme (MCS) is chosen under a 10% block-error-rate (BLER) constraint that channel non-stationarity undermines by breaking exchangeability. We drive the significance level $\alpha$t from a Conformal Test Martingale (CTM) used as a continuous control signal rather than a binary alarm: a windowed mixture martingale tracks non-exchangeability online and a bounded sigmoidal law maps its wealth to $\alpha$t. On real traces this restores BLER validity, matches error-counting baselines and—unlike them—returns to its nominal operating point once transient drift subsides.

Cite this Paper

BibTeX
@InProceedings{pmlr-v329-minotti26a, title = {Adaptive Conformal Prediction for 5G Link Adaptation under Distribution Shift}, author = {Minotti, Emanuele and Dong, Genghua and Koudouridis, George}, booktitle = {Proceedings of the Fifteenth Symposium on Conformal and Probabilistic Prediction with Applications}, pages = {1049--1052}, 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/minotti26a/minotti26a.pdf}, url = {https://proceedings.mlr.press/v329/minotti26a.html}, abstract = {In 5G link adaptation a modulation and coding scheme (MCS) is chosen under a 10% block-error-rate (BLER) constraint that channel non-stationarity undermines by breaking exchangeability. We drive the significance level $\alpha$t from a Conformal Test Martingale (CTM) used as a continuous control signal rather than a binary alarm: a windowed mixture martingale tracks non-exchangeability online and a bounded sigmoidal law maps its wealth to $\alpha$t. On real traces this restores BLER validity, matches error-counting baselines and—unlike them—returns to its nominal operating point once transient drift subsides.} }
Endnote
%0 Conference Paper %T Adaptive Conformal Prediction for 5G Link Adaptation under Distribution Shift %A Emanuele Minotti %A Genghua Dong %A George Koudouridis %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-minotti26a %I PMLR %P 1049--1052 %U https://proceedings.mlr.press/v329/minotti26a.html %V 329 %X In 5G link adaptation a modulation and coding scheme (MCS) is chosen under a 10% block-error-rate (BLER) constraint that channel non-stationarity undermines by breaking exchangeability. We drive the significance level $\alpha$t from a Conformal Test Martingale (CTM) used as a continuous control signal rather than a binary alarm: a windowed mixture martingale tracks non-exchangeability online and a bounded sigmoidal law maps its wealth to $\alpha$t. On real traces this restores BLER validity, matches error-counting baselines and—unlike them—returns to its nominal operating point once transient drift subsides.
APA
Minotti, E., Dong, G. & Koudouridis, G.. (2026). Adaptive Conformal Prediction for 5G Link Adaptation under Distribution Shift. Proceedings of the Fifteenth Symposium on Conformal and Probabilistic Prediction with Applications, in Proceedings of Machine Learning Research 329:1049-1052 Available from https://proceedings.mlr.press/v329/minotti26a.html.

Related Material