Quantum Fourier Generative Models Trainable at Large Scale

• URL: http://arxiv.org/abs/2606.28483v1
• Date: Fri, 26 Jun 2026 18:00:00 GMT
• Title: Quantum Fourier Generative Models Trainable at Large Scale
• Abstract summary: We propose an algorithmic framework for building and training quantum generative models.<n>We develop a distinct training strategy where training is enabled at large scale by log-likelihood loss.<n>We demonstrate the efficiency of the suggested framework by validating loss estimation at the scale of over 1000 qubits.
• Score: 13.839852906168787
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose an algorithmic framework for building and training quantum generative models corresponding to multivariate probability distributions. Our model uses parallel Fourier feature maps for embedding continuous-valued variables combined with a forrelation-type quantum circuit for tuning Fourier coefficients of the quantum model. Crucially, we develop a distinct training strategy where training is enabled at large scale by log-likelihood loss with unbiased Monte Carlo estimator based on Parseval's identity. Unlike prior work that relied on maximal mean discrepancy (MMD) loss, our approach goes beyond matching just low frequency moments, while enabling efficient classical training. Once the model is trained, we use inverse quantum Fourier transforms to map it into a separate sampling circuit in the computational basis. We demonstrate the efficiency of the suggested framework by validating loss estimation at the scale of over 1000 qubits on a single GPU. We show that univariate and bivariate models with highly non-trivial structure can be trained to low total variation distance, while fine-tuned IQP models with MMD loss show poor performance. Comparing to classical baselines represented by normalizing flow and diffusion models, we show that our approach avoids oversmoothing and preserves multi-modal structure of the target. Finally, we have deployed the trained models on superconducting quantum devices, successfully sampling distributions with per-sample execution times of approximately $300\,μ\mathrm{s}$. Our work shows that quantum generative models with the train-on-classical deploy-on-quantum approach can provide both high-quality structure at increased scale and fast sampling access needed for inference.

Related papers

• "Train classical, deploy quantum" requires rethinking generalization [42.16343861129583]
  We benchmark a broad set of quantum and classical generative models by direct sampling.<n>We show that models trained with a moment-matching loss generally show worse generalization than the likelihood-trained models.
  arXiv  Detail & Related papers  (2026-08-31T17:26:27Z)
• Scalable Lindblad Noise Learning via Stochastic Tensor-Network Simulation [48.887627688666974]
  Learning dissipation rates in large-scale open quantum systems is a major obstacle for near-term quantum technologies.<n>Here, we propose a scalable noise-learning framework for Lindblad dissipation rates that combines a simulation method, the Jump Method (TJM)<n>We demonstrate the approach on two noise models in the Ising model, in which independent dissipation rates are learned for each site up to $N_mathrmsite=16$.<n>This combination of scalable numerics and rigorous theoretical guarantees positions TJM-based noise learning as a practical foundation for characterizing dissipation in large quantum devices.
  arXiv  Detail & Related papers  (2026-08-25T15:07:11Z)
• Quantum Incremental Learning with Mixed State Prototypes [53.319426778720434]
  We introduce a novel quantum incremental learning framework based on trainable mixed-state prototypes.<n>Our model achieves high-dimensional feature concentration using a minimal number of qubits.
  arXiv  Detail & Related papers  (2026-08-11T04:22:42Z)
• Sample-based training of quantum generative models [1.3521721488318912]
  We introduce a training framework that extends the principle of contrastive divergence to quantum models.<n>By deriving the circuit structure and providing a general recipe for constructing it, we obtain quantum circuits that generate the samples required for parameter updates.
  arXiv  Detail & Related papers  (2025-11-14T19:00:02Z)
• Inference-Time Scaling of Diffusion Language Models with Particle Gibbs Sampling [70.8832906871441]
  We study how to steer generation toward desired rewards without retraining the models.<n>Prior methods typically resample or filter within a single denoising trajectory, optimizing rewards step-by-step without trajectory-level refinement.<n>We introduce particle Gibbs sampling for diffusion language models (PG-DLM), a novel inference-time algorithm enabling trajectory-level refinement while preserving generation perplexity.
  arXiv  Detail & Related papers  (2025-07-11T08:00:47Z)
• Overcoming Dimensional Factorization Limits in Discrete Diffusion Models through Quantum Joint Distribution Learning [79.65014491424151]
  We propose a quantum Discrete Denoising Diffusion Probabilistic Model (QD3PM)<n>It enables joint probability learning through diffusion and denoising in exponentially large Hilbert spaces.<n>This paper establishes a new theoretical paradigm in generative models by leveraging the quantum advantage in joint distribution learning.
  arXiv  Detail & Related papers  (2025-05-08T11:48:21Z)
• Quantum Chebyshev Probabilistic Models for Fragmentation Functions [14.379311972506791]
  We study fragmentation functions(FFs) of charged pions and kaons from single-inclusive hadron annihilation in electron-positron.<n>Our results highlight the growing potential of quantum generative modeling for addressing problems in scientific discovery and advancing data analysis in high-energy physics.
  arXiv  Detail & Related papers  (2025-03-20T12:09:44Z)
• RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models [53.571195477043496]
  We propose an algorithm named Rotated Straight-Through-Estimator (RoSTE)<n>RoSTE combines quantization-aware supervised fine-tuning (QA-SFT) with an adaptive rotation strategy to reduce activation outliers.<n>Our findings reveal that the prediction error is directly proportional to the quantization error of the converged weights, which can be effectively managed through an optimized rotation configuration.
  arXiv  Detail & Related papers  (2025-02-13T06:44:33Z)
• Parameterized quantum circuits as universal generative models for continuous multivariate distributions [1.118478900782898]
  ized quantum circuits have been extensively used as the basis for machine learning models in regression, classification, and generative tasks. In this work, we elucidate expectation value sampling-based models and prove the universality of such variational quantum algorithms. Our results may help guide the design of future quantum circuits in generative modelling tasks.
  arXiv  Detail & Related papers  (2024-02-15T10:08:31Z)
• Are Quantum Circuits Better than Neural Networks at Learning Multi-dimensional Discrete Data? An Investigation into Practical Quantum Circuit Generative Models [0.0]
  We show that multi-layer parameterized quantum circuits (MPQCs) are more expressive than classical neural networks (NNs) We organize available sources into a systematic proof on why MPQCs are able to generate probability distributions that cannot be efficiently simulated classically. We address practical issues such as how to efficiently train a quantum circuit with only limited samples, how to efficiently calculate the gradient (quantum) and how to alleviate modal collapse.
  arXiv  Detail & Related papers  (2022-12-13T05:31:31Z)
• Importance sampling for stochastic quantum simulations [68.8204255655161]
  We introduce the qDrift protocol, which builds random product formulas by sampling from the Hamiltonian according to the coefficients. We show that the simulation cost can be reduced while achieving the same accuracy, by considering the individual simulation cost during the sampling stage. Results are confirmed by numerical simulations performed on a lattice nuclear effective field theory.
  arXiv  Detail & Related papers  (2022-12-12T15:06:32Z)
• Protocols for Trainable and Differentiable Quantum Generative Modelling [21.24186888129542]
  We propose an approach for learning probability distributions as differentiable quantum circuits (DQC) We perform training of a DQC-based model, where data is encoded in a latent space with a phase feature map, followed by a variational quantum circuit. This allows fast sampling from parametrized distributions using a single-shot readout.
  arXiv  Detail & Related papers  (2022-02-16T18:55:48Z)
• Generalization Metrics for Practical Quantum Advantage in Generative Models [68.8204255655161]
  Generative modeling is a widely accepted natural use case for quantum computers. We construct a simple and unambiguous approach to probe practical quantum advantage for generative modeling by measuring the algorithm's generalization performance. Our simulation results show that our quantum-inspired models have up to a $68 times$ enhancement in generating unseen unique and valid samples.
  arXiv  Detail & Related papers  (2022-01-21T16:35:35Z)
• Learnability of the output distributions of local quantum circuits [53.17490581210575]
  We investigate, within two different oracle models, the learnability of quantum circuit Born machines. We first show a negative result, that the output distributions of super-logarithmic depth Clifford circuits are not sample-efficiently learnable. We show that in a more powerful oracle model, namely when directly given access to samples, the output distributions of local Clifford circuits are computationally efficiently PAC learnable.
  arXiv  Detail & Related papers  (2021-10-11T18:00:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.