Uncertainty-aware quantum machine learning based on Dempster-Shafer theory
Authors: Marie Kempkes, Jakob Spiegelberg, Evert van Nieuwenburg, Vedran Dunjko
Organizations: Leiden University, Niels Bohrweg 1, 2333 CA Leiden, Netherlands · Volkswagen Group Innovation, Berliner Ring 2, 38440 Wolfsburg, Germany
A large body of work in quantum machine learning has centered on characterizing the expressivity and performance of quantum models. In contrast, little attention has been paid to the reliability of predictions beyond average performance measures such as accuracy. In this work, we introduce an uncertainty-aware quantum classification framework based on Dempster-Shafer theory. This theory allows to express uncertainty through weights assigned not only to individual classification labels but to sets of labels. We introduce a training strategy that enables parameterized quantum circuits to learn such assignments directly from data. This provides an efficient way to prepare the corresponding quantum states and enables the application of different post-processing strategies. In particular, it offers a practical setting for quantum Dempster-Shafer fusion procedures with polynomial resource requirements, even when the corresponding mass functions are defined over exponentially many subsets. Overall, our work represents a step toward enabling quantum models to express uncertainty about their predictions, thereby extending the evaluation of quantum models beyond predictive performance alone.
Figures & tables
Figure 1: Conceptual overview of the proposed method. A parameterized quantum circuit is trained using the loss in Eq. ( 7 ). The resulting basis state probabilities encode masses from Dempster–Shafer theory (see Section III.1 ), which are subsequently used in different post-processing steps (Section III.2 ).
Figure 2: Illustration of the influence of the loss function parameter λ . (a) Exemplary mass vector for a representative MNIST image of the digit 3 for different values of λ . Smaller values of λ increase the mass assigned to larger subsets, resulting in more imprecise hypotheses. (b) Average mass assigned to subsets of different cardinalities ∣S∣ as a function of λ , quantitatively confirming the trend observed in panel (a).
Figure 3: Empirical sparsity of the learned mass vector beyond the ideal setting of Proposition 2 . The quantity kτ denotes the minimum number of subsets required to account for a fraction τ of the total mass. Panels (a) and (c) show kτ as a function of the error threshold ε for different numbers of qubits, while panels (b) and (d) show the dependence on the number of qubits for fixed values of ε . As the training error increases, the mass functions become less sparse. Moreover, for fixed error thresholds, kτ grows rapidly with the number of qubits.
Uncertainty metric
MNIST
CIFAR10
Summed singleton plausibility
0.83
0.707
Average plausibility-belief gap
0.82
0.684
Credal set volume
0.54
0.625
Table 1: AUROC values for out-of-distribution detection on two datasets using different uncertainty metrics derived from the Dempster-Shafer quantum classifier. All metrics are defined in Section III.2 .
Figure 4: Mass fusion improves classification performance. Four individual classifiers are trained on disjoint patches of MNIST images, obtained by splitting each image into four parts, and evaluated separately. The fused classifier combines learned mass functions using Dempster’s rule as described in Section III.2 . Bars show test accuracy of each individual classifier and of the fused model; the dashed line indicates the mean accuracy of the individual classifiers.
Appendix figures & tables1 asset
Supplementary material from the paper’s appendix.
Appendix
Figure A1: Average empty-set mass as a function of the number of classes. (a) MNIST and (b) CIFAR10. Error bars denote the standard deviation across test samples. Although the proposed encoding does not explicitly enforce the Dempster-Shafer constraint m(∅)=0 , the learned mass assigned to the empty set decreases with the number of classes and is negligible for the larger-scale settings considered in the main experiments.
We propose a variational quantum classifier operating on high dimensional deep representations via amplitude encoding, stabilized by a learnable classical pre encoding layer.By combining normalized amplitude embeddings with bounded quantum observables, the resulting model induces a structured and smooth hypothesis class with controlled sensitivity to input variations. Model reliability is assessed using SAFE-AI metrics derived from the Cramer von Mises divergence, enabling consistent evaluation across accuracy, robustness, and explainability dimensions. Empirical results show that the proposed quantum model provides competitive predictive performance compared with strong classical baselines while exhibiting a more balanced SAFE reliability profile, with improved robustness to noise and stability under structured feature removal. These findings suggest that variational quantum circuits offer a principled mechanism for stability oriented SAFE learning in safety critical settings.
Ying Chen, Paolo Giudici, Vasily Kolesnikov +1
National University of Singapore · University of Pavia
Understanding generalization is essential for assessing the practical viability of quantum machine learning. In many applications, quantum models operate on classical data that must first be encoded into quantum states, making the encoding part of the effective hypothesis class. We develop a margin-based generalization framework for this setting, covering both fixed and trainable quantum data encodings. For fixed encodings, the existing margin bound transfers unchanged. For trainable encodings, we derive a bound using a two-scale covering argument that combines the original margin-dependent term with an additive encoding-capacity term of order O~(L/m), where L is the number of trainable encoding parameters and m is the training-sample size. Across 19,440 simulated training runs spanning various image datasets, circuit architectures, and optimization settings, the inverse margin performs best among five baseline and two bound-derived complexity measures under conditional-independence and 90th-percentile sign-error criteria, within bootstrap uncertainty. These results provide a unified margin-based view of generalization in quantum machine learning with classical data.
Ju-Young Ryu, Tak Hur, Daniel K. Park
Korea Institute of Science and Technology Information, Republic of Korea · Department of Statistics and Data Science, Yonsei University, Republic of Korea · Department of Applied Mathematics, University of Waterloo, Canada +2
Quantum machine learning is often motivated by the exponentially large state space of quantum systems, but this promise leaves a basic generalization problem unresolved: how can a learner assign different meanings to unseen quantum directions when the training data provide no preferred basis, measurement frame, or other orienting structure? We address this identifiability problem by formulating supervised learning without an external quantum reference frame, so that predictions cannot depend on an arbitrary choice of Hilbert-space coordinates. This requirement forces the learned classifier to preserve every unitary symmetry left unbroken by the training data. We prove that whenever the training states fail to span the full Hilbert space, all pure states orthogonal to their span must receive the same prediction -- even when those states are mutually orthogonal and perfectly distinguishable once an appropriate measurement is supplied. The limitation is therefore not caused by state discrimination, optimization, or computational power, but by missing reference information. We further establish a robust version under weak symmetry breaking and show that learning generic unstructured concepts on multiqubit systems requires exponentially many independently oriented training directions. Numerical illustrations visualize the resulting prediction collapse and its controlled relaxation. Our results identify feature maps, measurement bases, Hamiltonians, locality, symmetry priors, architectures, and sufficiently diverse training states as operational resources for generalization. The central implication is that Hilbert-space dimension alone is not a learnable feature space: successful QML must specify the physical structure that gives unseen quantum directions semantic meaning.
Jeongho Bang
Institute for Convergence Research and Education in Advanced Technology, Yonsei University, Seoul 03722, Republic of Korea · Department of Quantum Information, Yonsei University, Incheon 21983, Republic of Korea