Reliable decision-making with quantum neural networks on NISQ hardware requires uncertainty estimates that remain meaningful under finite-shot measurement noise and distribution shift. This study introduces an end-to-end pipeline that combines Bayesian variational quantum circuits with post hoc probability calibration and conformal prediction to produce coverage-controlled prediction sets. Across shot budgets from 128 to 4096 shots, the Bayesian variational circuit improves accuracy from 0.828 to 0.839 at 128 shots and from 0.862 to 0.892 at 4096 shots, while reducing negative log-likelihood from 0.462 to 0.448 at 128 shots and from 0.392 to 0.357 at 4096 shots. Calibration preserves accuracy while further lowering negative log-likelihood to 0.432 at 128 shots and 0.350 at 4096 shots, and reduces expected calibration error from 0.058 to 0.027. Conformalization achieves empirical coverage of 0.952 at miscoverage 0.05, with average set size 1.39 and singleton rate 0.71, and maintains coverage between 0.944 and 0.948 under feature corruption and subpopulation shift, where deterministic accuracy degrades to 0.801 and 0.774, respectively, while the Bayesian model retains 0.842 and 0.816. Ablations identify an operational knee at circuit depth 8, and show diminishing returns beyond 8 posterior samples per prediction, supporting deployment-efficient uncertainty control for quantum learning.
Reliable decision-making with quantum neural networks on NISQ hardware requires uncertainty estimates that remain meaningful under finite-shot measurement noise and distribution shift. This study introduces an end-to-end pipeline that combines Bayesian variational quantum circuits with post hoc probability calibration and conformal prediction to produce coverage-controlled prediction sets. Across shot budgets from 128 to 4096 shots, the Bayesian variational circuit improves accuracy from 0.828 to 0.839 at 128 shots and from 0.862 to 0.892 at 4096 shots, while reducing negative log-likelihood from 0.462 to 0.448 at 128 shots and from 0.392 to 0.357 at 4096 shots. Calibration preserves accuracy while further lowering negative log-likelihood to 0.432 at 128 shots and 0.350 at 4096 shots, and reduces expected calibration error from 0.058 to 0.027. Conformalization achieves empirical coverage of 0.952 at miscoverage 0.05, with average set size 1.39 and singleton rate 0.71, and maintains coverage between 0.944 and 0.948 under feature corruption and subpopulation shift, where deterministic accuracy degrades to 0.801 and 0.774, respectively, while the Bayesian model retains 0.842 and 0.816. Ablations identify an operational knee at circuit depth 8, and show diminishing returns beyond 8 posterior samples per prediction, supporting deployment-efficient uncertainty control for quantum learning.
Uncertainty quantification (UQ) is essential for deploying machine learning models in safety-critical physical systems, yet classical Bayesian approaches incur substantial computational overhead. We establish a formal connection between Born-rule measurement statistics from variational quantum circuits (VQCs) and Bayesian posterior uncertainty, proving that repeated quantum measurements naturally produce calibrated prediction intervals without requiring explicit Bayesian neural network (BNN) machinery. We demonstrate this framework on physics-constrained VQCs trained on PDE residuals. Systematic experiments comparing quantum shot-based UQ against MC Dropout and Deep Ensemble baselines show that quantum UQ achieves coverage probabilities within 1-3% of target confidence levels at N >= 5000 shots, while MC Dropout systematically over-covers by 4-5%. Physics-constrained circuits reduce the expected calibration error (ECE) by 34-40% compared to unconstrained counterparts, with interval widths 14-30% narrower at equivalent coverage. Information-theoretic analysis reveals that quantum circuits extract ~15% more bits of UQ information per evaluation than MC Dropout and ~42% more than Deep Ensembles (M = 10), owing to the exponential Hilbert space accessible through Born-rule sampling. These results establish quantum measurement statistics as a principled, computationally efficient framework for uncertainty quantification in physics-informed learning.
Quantum machine learning on noisy intermediate-scale quantum (NISQ) devices often suffers from noise sensitivity, small-data overfitting, and miscalibrated predictive confidence. We propose an uncertainty-aware hybrid Bayesian quantum neural network (BQNN) that couples a Bayesian convolutional front-end with a parameterized quantum circuit (PQC), forming a three-stage pipeline: Bayesian feature extraction, quantum state evolution, and classical decision making. For 28 ×28 grayscale inputs, the front-end uses an 8-filter 3 ×3 Bayesian convolution followed by 2 ×2 max-pooling and a fully connected layer to produce a 10-dimensional embedding, which is mapped to four rotation angles and encoded on 4 qubits. Two parameterized quantum circuit designs are considered for the quantum classification layer. On MNIST and Fashion-MNIST, repeated experiments over five independent random seeds show that the proposed BQNN variants consistently outperform the corresponding QCNN baselines. On MNIST, BQNN-2 achieves a mean best test accuracy of 95.46 ± 0.36%, a mean final test accuracy of 95.44 ± 0.38%, and a mean final test loss of 0.169 ± 0.012. On Fashion-MNIST, BQNN-1 attains the best mean overall performance, with a mean best test accuracy of 87.59 ± 0.62%, a mean final test accuracy of 87.49 ± 0.73%, and a mean final test loss of 0.385 ± 0.017, while BQNN-2 exhibits slightly smaller run-to-run variation. Additional representative comparisons with QNN baselines under the same training configuration further suggest faster convergence and higher peak accuracy for BQNN. Using 30 Monte-Carlo forward passes, BQNN achieves better calibration (ECE 0.007-0.009) than QCNN (ECE 0.016-0.020), thereby reducing overconfident predictions. Additional robustness experiments under noisy mixed-state simulation further show that, under depolarizing noise, BQNN consistently preserves higher peak test accuracy than QCNN across both circuit variants on MNIST, demonstrating improved robustness in NISQ-like noisy settings.
To make predictions on the future states of engineering systems, prognostics has been increasingly relying on data-driven models and machine learning. Recent work has also looked at the potential of quantum machine learning to provide insight on the health state of systems. Nevertheless, these approaches treated the quantum component only as a deterministic predictor, in fact disregarding the uncertainty information. In this work, we propose a different approach to exploiting quantum circuits in prognostics. We focus on Bayesian learning of neural networks for Remaining Useful Life (RUL) prediction and uncertainty quantification. Here, the quantum circuit is introduced not as a data-driven model, but as a generator of neural network weights. Using Variational Inference, the quantum circuit can be trained to approximate the true posterior of the classical machine learning predictor. The overall method retains the data-processing ability of state-of-the-art machine learning models, while exploiting the quantum circuit to introduce uncertainty by sampling the modelspace from a distribution that is classically nontrivial. We validate our approach on the task of predicting the End of Discharge of Li-ion batteries, using data generated from a simulator with tunable process uncertainty, and we compare the predictions obtained through quantum sampling with those from Flipout Bayesian neural networks, heteroscedastic neural networks and Monte Carlo Dropout. The results show that our quantum circuits learn to approximate the weight posterior and that the resulting data-driven models demonstrate accuracy and uncertainty quantification that is comparable if not superior to the baselines. Overall, our work demonstrates the potential of quantum computing for uncertainty-aware prognostics, and sets the stage for further investigations in this area.
Quantum machine learning is a promising programming paradigm for the optimization of quantum algorithms in the current era of noisy intermediate scale quantum (NISQ) computers. A fundamental challenge in quantum machine learning is generalization, as the designer targets performance under testing conditions, while having access only to limited training data. Existing generalization analyses, while identifying important general trends and scaling laws, cannot be used to assign reliable and informative “error bars” to the decisions made by quantum models. In this article, we propose a general methodology that can reliably quantify the uncertainty of quantum models, irrespective of the amount of training data, of the number of shots, of the ansatz, of the training algorithm, and of the presence of quantum hardware noise. The approach, which builds on probabilistic conformal prediction, turns an arbitrary, possibly small, number of shots from a pre-trained quantum model into a set prediction, e.g., an interval, thatprovablycontains the true target with any desired coverage level. Experimental results confirm the theoretical calibration guarantees of the proposed framework, referred to asquantum conformal prediction.
Quantum fidelity estimation is a fundamental task in quantum information and computing to benchmark the quality of quantum states, and hence of quantum processes, on noisy quantum hardware. Point estimates of fidelity by existing methods generally lack the rigorous uncertainty quantification required for reliable preparation and verification of these tasks. While Bayesian and bootstrap frameworks are widely used for uncertainty quantification, they are sensitive to model misspecification or lack formal coverage guarantees in non-asymptotic regimes. This paper introduces a hybrid "Bayesian-informed" conformal prediction-based framework to provide distribution-free, rigorous prediction intervals for quantum state fidelity estimation which can be used, with care, to approximate confidence intervals with respect to the quantum randomness of Born's rule. The framework requires a point estimator, and we consider both classical point estimators as well as data-driven neural net estimators. We evaluate the robustness of the methodology across a diverse range of experimental challenges, including finite-sample noise, tomographic incompleteness, physical model error, and out-of-distribution data. Our results demonstrate that conformalized estimators maintain statistical validity where traditional methods fail, offering a scalable and reliable approach for the verification of modern quantum systems. The best performing variant of our methodology is based on a class-conditional conformal prediction, as this most closely approximates the conditional coverage desired for a true confidence interval.
Abstract Operator learning enables fast surrogate modelling of high-dimensional dynam-ical systems, but existing approaches face two fundamental limitations: the quadratic cost of dense neural layers and unreliable uncertainty quantification in safety-critical settings. We propose Conformalized Quantum Deep Operator Network (DeepONet) Ensembles, a framework that addresses both challenges simultaneously. Using Quantum Orthogonal Neural Networks (QOrthoNNs), we characterize the resource regime in which their established˜︁established˜︁ O(n) hidden-layer running-time scaling improves on the O(n 2) cost of a classical dense layer. To quantify uncertainty, we combine ensemble predictions with split conformal calibration. For a new input–output function pair jointly exchangeable with the calibration pairs, we prove a finite-sample, distribution-free lower bound on the expected fraction of covered query locations. As a secondary proof-of-concept, we explore hybrid classical–quantum architectures and superposed execution to manage ensemble runtime and hardware requirements. Experiments on synthetic operator benchmarks and real-world power-system dynamics show accurate predictions under ideal simulation and empirical coverage near the target under both ideal conditions and selected compact-circuit simulations with depolarizing 1 or device-calibrated composite noise. Together, these results connect resource-aware scalability analysis with finite-sample uncertainty guarantees for quantum operator learning.