We study certified upper bounds on Lipschitz constants for hybrid quantum-classical decision models, which combine classical neural-network layers with parameterized quantum circuits. We pair an SDP-based certificate for classical layers with an exact spectral characterization for probability-output quantum models. For hybrid architectures, these componentwise estimates are connected through the encoding maps to obtain a certified composition bound for the complete model. The resulting bounds support sensitivity analyses relevant to robustness, stability, generalization, and fairness.
Figures & tables
Training method
Certified bound
Clean accuracy
Naive
8.288
100.0%
Lipschitz regularization
5.784
100.0%
PGD
6.682
93.3%
Table 1: Certified Lipschitz upper bounds and clean test accuracy at epoch 30 for naive training, Lipschitz regularization, and PGD adversarial training.
Figure 1: Certified Euclidean Lipschitz upper bound over 30 training epochs for naive training with ℓ1 , squared ℓ2 , and ℓ∞ data losses. The original Iris labels are used in the left panel; all labels are replaced by a single class in the right panel. Regularization is disabled, and the certificate uses the Euclidean metric in both panels.
Figure 2: Final certified Euclidean Lipschitz upper bound as a function of the regularization coefficient for the ℓ1 , squared ℓ2 , and ℓ∞ training losses. The original Iris labels are used in the left panel and single-class labels in the right; each panel shows the 20-point sweep over λ∈[10−4,0.5] . For the original labels, the reduction in the bound at larger coefficients accompanies a loss in clean test accuracy, as detailed in the text.
Figure 3: Training trajectories for naive training, Lipschitz-regularized training, and PGD adversarial training with squared ℓ2 data loss. The left panel reports the certified Euclidean Lipschitz upper bound; the right panel reports clean test accuracy (not adversarial accuracy). The epoch-30 values are summarized in Table 1 .
Hybrid quantum-classical machine learning combines quantum circuits or annealers with classical models for learning, prediction, generation, and optimization.
The global Lipschitz constant of a neural network is related to robustness and generalization, yet unlike in many classical models, it is not plainly legible from the parameters. This has motivated sophisticated verification algorithms, especially semidefinite programming (SDP) based on incremental quadratic constraints on the activation functions, to improve on the fast but often loose product of layerwise Lipschitz constants (the trivial bound). We ask why Lipschitz verification is a problem in the first place. Our answer is that the difficulty is structural: estimating a network's Lipschitz constant requires knowing which hidden states are reachable, and reachability is NP-hard. If P!=NP, then reachability is a barrier to any polynomial-time algorithm. Through explicit constructions, we show that this blindness can force SDP-based bounds to inherit the same qualitative failures as the trivial bound, including but not limited to polynomial per-layer conservatism. We show that the difficulties of NP-hard questions are not isolated to worst-case computational reductions, but actually afflict every instance of the verification problem. Thus SDP is not sufficient for Lipschitz verification. We also argue that it is not necessary: several apparent failures of the trivial bound arise from removable parameterization pathologies, and can be mitigated by optimizing or regularizing the trivial bound itself. We demonstrate this claim via a "spherical cow" linear model and numerical proofs of concept. While the main contribution is theoretical and negative, we finally motivate a novel form of trigonometric layers that do not need biases for universal approximation. Combined with trivial bound regularization, they make the trivial bound provably and practically tight.
Simon Kuang, Yuezhu Xu, S. Sivaranjani +1
Department of Mechanical and Aerospace Engineering University of California, Davis · Edwardson School of Industrial Engineering Purdue University
Quantum machine learning is a promising field for efficiently learning features of a dataset to perform a specified task, such as classification. Interval bound propagation (IBP) is a popular certified training method in classical machine learning, where the lower and upper bounds are tracked throughout the model. These bounds are used during training to ensure that the model is certified to predict the correct label even under adversarial perturbations. While IBP is successful in classical domain, there are limited certified training efforts in quantum domain. In this paper, we present quantum interval bound propagation (QIBP) to establish a certified training routine for quantum machine learning, certifying the accuracy of models under adversarial perturbations. We implement QIBP using both interval and affine arithmetic to explore the tradeoffs between the two implementations in terms of accuracy and other design considerations. Extensive evaluation demonstrates that the resulting certified trained models have robust decision boundaries, guaranteed to predict the correct class for the samples within the trained adversarial robustness bounds.
Quantum machine learning (QML) is increasingly recognized as one of the most promising near-term applications of quantum computing, viewed as a next-frontier candidate beyond purely classical approaches. Hybrid quantum-classical models operationalize this potential by embedding a parameterized quantum circuit within a model where all other components remain classical-a design already applied to chemistry simulation, financial modeling, and image classification. However, their deployment in privacy-sensitive, multi-party settings is constrained by the need to avoid centralizing raw data and by the requirement that modern quantum circuits remain parameter-efficient to stay trainable at scale. In this paper, we address these constraints by evaluating federated learning (FL) as a means of combining a hybrid quantum-classical active party with a classical passive party, using Sherpa.ai's Blind Vertical FL (SBVFL) protocol to avoid centralizing raw data, while drastically reducing communication. We construct the split multiplicative periodic parity (SMPP) benchmark, following common QML design practice. On this task, our simulations show that SBVFL raises accuracy from 0.7227 to 0.8757 compared to local training, closely approaching non-private centralized accuracy, and that the hybrid quantum-classical model achieves this with substantially fewer trainable parameters than the classical neural networks and random forest alternatives. These results show that FL enables high-performing, privacy-preserving quantum-classical collaboration without centralizing raw data.
Carlos Cano, Daniel M. Jimenez-Gutierrez, Diego Sal +4