cs.LG · 2606.12501 Copy arXiv ID · Jun 10, 2026 Save Policy-driven Conformal Prediction for Trustworthy QoT Estimation Authors: Kiarash Rezaei , Omran Ayoub , Paolo Monti , Carlos Natalino
Organizations: Department of Electrical Engineering, Chalmers University of Technology, 412 96 Gothenburg, Sweden · University of Applied Sciences and Arts of Southern Switzerland, 6928 Lugano, Switzerland
Abstract We propose Conformal QoT, a policy-driven framework that combines statistically guaranteed QoT estimation with operational decision policies, enabling reliable lightpath-feasibility predictions under domain shift and improving accuracy from 92% to 99.6% on open datasets.
Explore similar work Aug 7, 2026 · Joar Skalse, Edoardo Pona, Osvaldo Simeone +1 Conformal Prediction Black Box
May 16, 2026 · Chaymae Yahyati, Ismail Lamaakal, Khalid El Makkaoui +1 Quantization Distributional Fidelity
Jun 12, 2026 · Yanfei Zhou, Rizal Fathony, Nam H. Nguyen +1 Conformal Prediction Distribution Shifts
Aug 7, 2026 · cs.LG J/K move · Enter open · S save
Joar Skalse, Edoardo Pona, Osvaldo Simeone, Nicola Paoletti
King’s College London · Northeastern University London
Uncertainty quantification is essential when deploying machine learning models in safety-critical applications. Online conformal prediction (OCP) provides theoretically principled uncertainty quantification for arbitrary black-box classifiers and non-i.i.d. data streams by constructing prediction sets that are guaranteed to contain the true label at a user-specified frequency. OCP usually updates prediction sets using feedback from previously deployed predictions. We instead study an OCP setting beyond feedback: on each round, the learner can either output a prediction set or query the correct label, but not both. Thus, no deployed prediction is ever evaluated directly. We reduce this problem to a partial monitoring game in which prediction actions return no observation and a separate query action reveals the label. The reward function is constructed in a way that encourages the learner to output small prediction sets while ensuring that the correct label is covered with a sufficiently high probability. To solve this game, we develop OCP with queries (OCPQ) by adapting the label efficient forecaster of Cesa-Bianchi, Lugosi, and Stoltz (2004) to our setting. For any black box classifier and any (non-i.i.d.) oblivious data stream of length
T T T , OCPQ has
O ( T 2 / 3 ) O(T^{2/3}) O ( T 2/3 ) expected regret and expected coverage at least
β − O ( T − 1 / 3 ) β-O(T^{-1/3}) β − O ( T − 1/3 ) for a user-defined
β β β , while querying only an expected
T − 1 / 3 T^{-1/3} T − 1/3 fraction of rounds. This provides coverage comparable to bandit-based OCP methods while requiring no feedback from deployed prediction sets. Experiments on real-world datasets further demonstrate the effectiveness of our approach.