Instantaneous Quantum Polynomial Circuit Born Machines (IQP-QCBMs) have been proposed as quantum generative models that combine a classically tractable training objective - based on the maximum mean discrepancy (MMD) - with a potential quantum advantage motivated by sampling-complexity arguments. While recent works have explored this model across various application domains, fundamental questions remain: does the model suffer from exponentially vanishing loss gradients, known as the barren plateau problem - a pervasive obstacle in quantum machine learning - and how do regimes of trainability relate to regimes of possible quantum advantage? Here, we address both questions analytically. To study trainability, we derive closed-form expressions for the variances of the partial derivatives of the MMD loss function and establish general upper and lower bounds. We explicitly characterize how trainability depends on the generator set and the spectrum of the chosen kernel, identifying regimes in which low Hamming-weight kernels avoid exponential gradient suppression under structured topologies. Regarding potential quantum advantage, we reformulate the anti-concentration property in terms of the same generator-set quantities that govern trainability, enabling a unified analysis. We show that sparse IQP architectures can produce classically intractable output distributions while simultaneously remaining trainable, at least at lower-weight frequencies. Our analytical results corroborate the numerical observations of prior work and provide principled guidelines for designing scalable IQP-QCBM architectures.
Figures & tables
IQP Architecture
\absolutevalue\vta s.t. ra=O(logn)
No B.P.
Anti-concentration
Product State
O(logn)
✓
×
2D Lattice
O(logn)
✓
×
Sparse ER Graph ( p>2logn/n )
O(1)
✓
✓
Complete Graph
N.A.
×
✓
Table 1: Summary of the main result. We consider four architectures for the IQP circuit ( Fig. 2 ) and report the scaling of the critical rank ra ( Theorem 3.3 )—the key circuit property determining the scaling of the MMD partial derivatives. “No B.P.” indicates the absence of a barren plateau in the MMD loss with a suitable kernel choice, which is necessary for trainability at scale. “Anti-concentration” means L2 anti-concentration ( Definition 3.8 ) of the IQP-QCBM’s output distribution, which is needed to claim classical non-simulability.
Figure 1: Top: Scaling of the MMD derivative with respect to the number of qubits, measured on MNIST-inspired datasets and reporting the mean and standard deviation over 50 repetitions. Bottom: Trajectories of the MMD training loss for learning the 784 -qubit binarized MNIST dataset, with increasing sample sizes for estimating the MMD loss.
Appendix figures & tables1 asset
Supplementary material from the paper’s appendix.
Appendix
Figure 2: Illustration of the IQP architectures considered in this paper: product state ( Example 3.4 ), 2D lattice ( Example 3.5 ), sparse Erdős-Rényi graph ( Example 3.6 ), and complete graph ( Example 3.7 ).
Quantum Circuit Born Machines (QCBMs) offer a natural approach to generative machine learning by leveraging the Born rule. Recent work has provided a method to classically train QCBMs with Instantaneous Quantum Polynomial (IQP) circuits via the Maximum Mean Discrepancy (MMD) loss. Despite the assumed intractability of sampling from IQP circuits classically, their expectation values can be computed classically, enabling training of these IQP QCBMs. However, quantum machine learning (QML) models have various other challenges, including trainability issues caused by exponential concentration or barren plateaus. While these issues have been explored for parameters sampled from a uniform distribution, little work has been done to rigorously treat the use of arbitrary Gaussian initialization schemes. This work leverages Stein's lemma and Lipschitz concentration bounds for Gaussian random variables to provide an analytical lower bound of the variance of the gradient and a probabilistic concentration bound of the deviation of the gradient from its mean. It discusses strategies to either avoid or encourage exponential concentration, as well as the conditions under which barren plateaus are more likely to occur.
Gennaro De Luca, Vinayak Sharma, Aviral Shrivastava
Quantum circuit Born machines based on instantaneous quantum polynomial-time (IQP) circuits are natural candidates for quantum generative modeling, both because of their probabilistic structure and because IQP sampling is provably classically hard in certain regimes. Recent proposals focus on training IQP-QCBMs using Maximum Mean Discrepancy (MMD) losses built from low-body Pauli-Z correlators, but the effect of initialization on the resulting optimization landscape remains poorly understood. In this work, we address this by first proving that the MMD loss landscape suffers from barren plateaus for random full-angle-range initializations of IQP circuits. We then establish lower bounds on the loss variance for identity and an unbiased data-agnostic initialization. We then additionally consider a data-dependent initialization that is better aligned with the target distribution and, under suitable assumptions, yields provable gradients and generally converges quicker to a good minimum (as indicated by our training of circuits with 150 qubits on genomic data). Finally, as a by-product, the developed variance lower bound framework is applicable to a general class of non-linear losses, offering a broader toolset for analyzing warm-starts in quantum machine learning.
Sacha Lerch, Joseph Bowles, Ricard Puig +3
Institute of Physics, Ecole Polytechnique Fédérale de Lausanne (EPFL), CH-1015 Lausanne, Switzerland · Centre for Quantum Science and Engineering, École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland · Xanadu, Toronto, ON, M5G 2C8, Canada +3
Instantaneous quantum polynomial-time (IQP) Born machines are attractive quantum generative models, as certain IQP circuit families are conjectured to be hard to sample, yet they can be trained classically. Previously proposed conditional IQP Born machines make the parameters of the diagonal layer condition dependent. We introduce conditional IQP Born machines, in which the condition is encoded in the input state and a single IQP unitary is shared across conditions. Efficient sampling and amplitude-ratio evaluation for the reference state entering the diagonal layer suffice to obtain unbiased classical estimates of a conditional maximum mean discrepancy objective and its gradients. We show that input conditioning can represent conditional families that no diagonally conditioned IQP model with the same number of qubits can reproduce. For the sixteen-qubit Curie-Weiss spin model, a single conditional model captures the magnetization transition at held-out temperatures. Its mean total variation distance is six times lower than that of diagonal conditioning under the same protocol and comparable to that of classical generative models with up to seven times as many parameters. We also train conditional models classically with up to 2048 qubits, which reproduce the mean squared magnetization of the target away from the crossover. These results extend classically trained IQP Born machines to conditional generation.
Oriol Balló-Gimbernat, Emiliano Tolotti, Laia Domingo +2
Eurecat, Centre Tecnològic de Catalunya, Barcelona, Spain · Centre de Visió per Computador (CVC), Barcelona, Spain · Universitat Autònoma de Barcelona (UAB), Barcelona, Spain +1