Lightweight Online Multivariate Conformal Prediction

Abd Al-Rahman Hourani, Soundouss Messoudi, Sylvain Rousseau, Stefano Masi
Proceedings of the Fifteenth Symposium on Conformal and Probabilistic Prediction with Applications, PMLR 329:730-749, 2026.

Abstract

In the context of Advanced Driver Assistance Systems (ADAS), autonomous planning modules require rigorous uncertainty quantification alongside trajectory forecasting to ensure safe and proactive decision-making. While Conformal Prediction (CP) provides statistically valid confidence guarantees, its extension to multivariate spaces remains under-explored and, when implemented, often results in significant computational overhead that limits real-time applicability. To address this, we propose a Lightweight Online Multivariate Conformal Prediction (L-OMCP) framework designed to operate as an efficient top layer for existing prediction modules. Our approach constructs 2D confidence regions by introducing a joint non-conformity measure based on the empirical aspect ratio of spatial prediction errors, maintaining the lightweight computational overhead necessary for online deployment. To handle non-stationary driving dynamics, the framework utilizes an Exponential Moving Average (EMA) as its online update mechanism integrated with Adaptive Conformal Inference (ACI). This coupled formulation is projected into a bounded angular phase space to ensure robust stabilization and mitigate the impact of transient outliers or numerical instabilities. Comprehensive evaluations on synthetic scenarios and the real-world Renault dataset demonstrate that the proposed framework maintains the target coverage. Compared to both independent 1D baselines and state of the art multivariate methods, our approach generates tighter, context-aware bounding regions, providing a solution for real-time uncertainty quantification in ADAS.

Cite this Paper

BibTeX
@InProceedings{pmlr-v329-hourani26a, title = {Lightweight Online Multivariate Conformal Prediction}, author = {Hourani, Abd Al-Rahman and Messoudi, Soundouss and Rousseau, Sylvain and Masi, Stefano}, booktitle = {Proceedings of the Fifteenth Symposium on Conformal and Probabilistic Prediction with Applications}, pages = {730--749}, 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/hourani26a/hourani26a.pdf}, url = {https://proceedings.mlr.press/v329/hourani26a.html}, abstract = {In the context of Advanced Driver Assistance Systems (ADAS), autonomous planning modules require rigorous uncertainty quantification alongside trajectory forecasting to ensure safe and proactive decision-making. While Conformal Prediction (CP) provides statistically valid confidence guarantees, its extension to multivariate spaces remains under-explored and, when implemented, often results in significant computational overhead that limits real-time applicability. To address this, we propose a Lightweight Online Multivariate Conformal Prediction (L-OMCP) framework designed to operate as an efficient top layer for existing prediction modules. Our approach constructs 2D confidence regions by introducing a joint non-conformity measure based on the empirical aspect ratio of spatial prediction errors, maintaining the lightweight computational overhead necessary for online deployment. To handle non-stationary driving dynamics, the framework utilizes an Exponential Moving Average (EMA) as its online update mechanism integrated with Adaptive Conformal Inference (ACI). This coupled formulation is projected into a bounded angular phase space to ensure robust stabilization and mitigate the impact of transient outliers or numerical instabilities. Comprehensive evaluations on synthetic scenarios and the real-world Renault dataset demonstrate that the proposed framework maintains the target coverage. Compared to both independent 1D baselines and state of the art multivariate methods, our approach generates tighter, context-aware bounding regions, providing a solution for real-time uncertainty quantification in ADAS.} }
Endnote
%0 Conference Paper %T Lightweight Online Multivariate Conformal Prediction %A Abd Al-Rahman Hourani %A Soundouss Messoudi %A Sylvain Rousseau %A Stefano Masi %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-hourani26a %I PMLR %P 730--749 %U https://proceedings.mlr.press/v329/hourani26a.html %V 329 %X In the context of Advanced Driver Assistance Systems (ADAS), autonomous planning modules require rigorous uncertainty quantification alongside trajectory forecasting to ensure safe and proactive decision-making. While Conformal Prediction (CP) provides statistically valid confidence guarantees, its extension to multivariate spaces remains under-explored and, when implemented, often results in significant computational overhead that limits real-time applicability. To address this, we propose a Lightweight Online Multivariate Conformal Prediction (L-OMCP) framework designed to operate as an efficient top layer for existing prediction modules. Our approach constructs 2D confidence regions by introducing a joint non-conformity measure based on the empirical aspect ratio of spatial prediction errors, maintaining the lightweight computational overhead necessary for online deployment. To handle non-stationary driving dynamics, the framework utilizes an Exponential Moving Average (EMA) as its online update mechanism integrated with Adaptive Conformal Inference (ACI). This coupled formulation is projected into a bounded angular phase space to ensure robust stabilization and mitigate the impact of transient outliers or numerical instabilities. Comprehensive evaluations on synthetic scenarios and the real-world Renault dataset demonstrate that the proposed framework maintains the target coverage. Compared to both independent 1D baselines and state of the art multivariate methods, our approach generates tighter, context-aware bounding regions, providing a solution for real-time uncertainty quantification in ADAS.
APA
Hourani, A.A., Messoudi, S., Rousseau, S. & Masi, S.. (2026). Lightweight Online Multivariate Conformal Prediction. Proceedings of the Fifteenth Symposium on Conformal and Probabilistic Prediction with Applications, in Proceedings of Machine Learning Research 329:730-749 Available from https://proceedings.mlr.press/v329/hourani26a.html.

Related Material