Quantum Circuit Born Machines (QCBMs) are variational circuits whose goal is to encode a classical probability distribution in the measurement outcomes. With Hierarchical Learning (HL), we exploit the structure of the qubit mapping in this variational circuit to learn gates of a few qubits first before expanding to the whole system. Using adjoint simulation techniques on GPUs, we manage to load a 3 dimensional Gaussian distribution on 27 qubits to within 4% total variational distance (TVD). An additional benefit of this circuit structure is that it can reduce the number of gates required compared to other methods. To demonstrate the use, we benchmark the performance hierarchically learned circuits on IBM hardware with FireOpal optimization.
Quantum Circuit Born Machines (QCBMs) are variational circuits whose goal is to encode a classical probability distribution in the measurement outcomes. With Hierarchical Learning (HL), we exploit the structure of the qubit mapping in this variational circuit to learn gates of a few qubits first before expanding to the whole system. Using adjoint simulation techniques on GPUs, we manage to load a 3 dimensional Gaussian distribution on 27 qubits to within 4% total variational distance (TVD). An additional benefit of this circuit structure is that it can reduce the number of gates required compared to other methods. To demonstrate the use, we benchmark the performance hierarchically learned circuits on IBM hardware with FireOpal optimization.
We present hierarchical learning, a novel variational architecture for efficient training of large-scale variational quantum circuits. We test and benchmark our technique for distribution loading with quantum circuit born machines (QCBMs). With QCBMs, probability distributions are loaded into the squared amplitudes of computational basis vectors represented by bitstrings. Our key insight is to take advantage of the fact that the most significant (qu)bits have a greater effect on the final distribution and can be learned first. One can think of it as a generalization of layerwise learning, where some parameters of the variational circuit are learned first to prevent the phenomena of barren plateaus. We briefly review adjoint methods for computing the gradient, in particular for loss functions that are not expectation values of observables. We first compare the role of connectivity in the variational ansatz for the task of loading a Gaussian distribution on nine qubits, finding that 2D connectivity greatly outperforms qubits arranged on a line. Based on our observations, we then implement this strategy on large-scale numerical experiments with GPUs, training a QCBM to reproduce a 3-dimensional multivariate Gaussian distribution on 27 qubits up to ∼4% total variation distance. Though barren plateau arguments do not strictly apply here due to the objective function not being tied to an observable, this is to our knowledge the first practical demonstration of variational learning on large numbers of qubits. We also demonstrate hierarchical learning as a resource-efficient way to load distributions for existing quantum hardware (IBM's 7 and 27 qubit devices) in tandem with Fire Opal optimizations.
Variational quantum classifiers are promising for machine learning on noisy intermediate-scale quantum (NISQ) hardware, but flat circuits that act on all input features at once need many qubits, accumulate gate errors and suffer vanishing gradients as they widen. This paper proposes Hierarchical Quantum Learning (HQL), a two-level framework that splits a high-dimensional input into correlation-coherent feature groups, processes each group in a narrow 4-qubit module built from data re-uploading and quantum-convolutional pooling, and fuses the module outputs in a trainable quantum aggregator optimised end to end. HQL was implemented with an autograd statevector simulator and compared with three classical learners, a quantum-kernel SVM, a hardware-efficient VQC and a quantum convolutional neural network (QCNN) on three binary tasks with 30–64 features over five random splits. With identical inputs, HQL reached 69.6% accuracy on a 64-feature benchmark versus 62.4% for the best flat circuit, and 92.5% versus 90.3% on handwritten digits, using circuits half as wide. Its gradient variance stayed near 0.11 up to 32 qubits, while that of a hardware-efficient circuit fell 63.4-fold between 4 and 16 qubits. Classical baselines remained the most accurate on all tasks, which we report openly. HQL offers a practical, trainable route to variational learning on modular quantum processors.
Abstract In recent proposals of quantum circuit models for generative tasks, the discussion about their performance has been limited to their ability to reproduce a known target distribution. For example, expressive model families such as quantum circuit Born machines (QCBMs) have been almost entirely evaluated on their capability to learn a given target distribution with high accuracy. While this aspect may be ideal for some tasks, it limits the scope of a generative model’s assessment to its ability to memorize data rather than generalize . As a result, there has been little understanding of a model’s generalization performance and the relation between such capability and the resource requirements, e.g. the circuit depth and the amount of training data. In this work, we leverage upon a recently proposed generalization evaluation framework to begin addressing this knowledge gap. We first investigate the QCBM’s learning process of a cardinality-constrained distribution and see an increase in generalization performance while increasing the circuit depth. In the 12-qubit example presented here, we observe that with as few as 30 % of the valid data in the training set, the QCBM exhibits the best generalization performance toward generating unseen and valid data. Lastly, we assess the QCBM’s ability to generalize not only to valid samples, but to high-quality bitstrings distributed according to an adequately re-weighted distribution. We see that the QCBM is able to effectively learn the reweighted dataset and generate unseen samples with higher quality than those in the training set. To the best of our knowledge, this is the first work in the literature that presents the QCBM’s generalization performance as an integral evaluation metric for quantum generative models, and demonstrates the QCBM’s ability to generalize to high-quality, desired novel samples.
Abstract Quantum data loading plays a central role in quantum algorithms and quantum information processing. Many quantum algorithms hinge on the ability to prepare arbitrary superposition states as a subroutine, with claims of exponential speedups often predicated on access to an efficient data-loading oracle. In practice, constructing a circuit to prepare a generic n-qubit quantum state typically demands computational efforts scaling as O ( 2 n ) , posing a significant challenge for quantum algorithms to outperform their classical counterparts. To address this critical issue, various hybrid quantum–classical approaches have been proposed. However, many of these solutions favor simplistic circuit architectures, which are susceptible to substantial optimization challenges. In this study, we harness quantum circuits as Born machines to generate probability distributions. Drawing inspiration from methods used to investigate electronic structures in quantum chemistry and condensed matter physics, we propose a framework called Adaptive Circuit Learning of Born Machine, which dynamically expands the ansatz circuit. Our algorithm is designed to selectively integrate two-qubit entangled gates that best capture the intricate entanglement present within the target state. Empirical experiments underscore the efficacy of our approach in encoding real-world data through amplitude embedding, demonstrating not only compliance with but also enhancement over the performance benchmarks set by prior research.
Quantum generative models use the intrinsic probabilistic nature of quantum mechanics to learn and reproduce complex probability distributions. In this paper, we present an implementation of a 3-qubit quantum circuit Born machine trained to model a 3-bit Gaussian distribution using a Kullback-Leibler (KL) divergence loss and parameter-shift gradient optimization. The variational quantum circuit consists of layers of parameterized rotations and entangling gates, and is optimized such that the Born rule output distribution closely matches the target distribution. We detail the mathematical formulation of the model distribution, the KL divergence cost function, and the parameter-shift rule for gradient evaluation. Training results on a statevector simulator show that the KL divergence is minimized to near zero, and the final generated distribution aligns quantitatively with the target probabilities. We analyze the convergence behavior and discuss the implications for scalability and quantum advantage. Our results demonstrate the feasibility of small-scale quantum generative learning and provide insight into the training dynamics of quantum circuit models.
Data scarcity and class imbalance are persistent challenges in machine learning that degrade model generalization and introduce predictive bias. We present a hybrid quantum-classical framework for synthetic data generation using a Quantum Circuit Born Machine (QCBM) to address these limitations. The proposed approach exploits quantum mechanical properties -- superposition and entanglement -- within a parameterized variational quantum circuit to model complex probability distributions that are difficult for classical generative methods to capture. Experiments are conducted on two tabular benchmark datasets: the Iris dataset and the Telco Customer Churn dataset. Preprocessing includes normalization and PCA-based dimensionality reduction to enable efficient basis encoding for quantum circuits. The QCBM is trained by minimizing Kullback-Leibler (KL) divergence between real and generated data distributions using a gradient-based parameter-shift optimization rule. Augmenting training data with QCBM-generated synthetic samples at 40-50% of the minority class improves F1-score by approximately 5-15% and minority-class recall by 10-25%. Cross-domain evaluations (Train on Synthetic, Test on Real; and Train on Real, Test on Synthetic) reveal a performance gap of only 3-10%, indicating strong distributional fidelity. Comparative analysis against classical oversampling methods -- SMOTE, Borderline-SMOTE, KMeansSMOTE, and SVM-SMOTE -- shows that QCBM achieves competitive classification performance and produces lower Maximum Mean Discrepancy (MMD) on the Telco dataset, suggesting superior structural similarity in certain imbalanced settings. These findings establish QCBM as a viable complementary tool for data augmentation, particularly for low-dimensional structured tabular data with class imbalance.