Trainability barriers and opportunities in quantum generative modeling

• URL: http://arxiv.org/abs/2305.02881v1
• Date: Thu, 4 May 2023 14:45:02 GMT
• Title: Trainability barriers and opportunities in quantum generative modeling
• Authors: Manuel S. Rudolph, Sacha Lerch, Supanut Thanasilp, Oriel Kiss, Sofia Vallecorsa, Michele Grossi, Zo\"e Holmes
• Abstract summary: We investigate the barriers to the trainability of quantum generative models. We show that using implicit generative models with explicit losses leads to a new flavour of barren plateau. We propose a new local quantum fidelity-type loss which, by leveraging quantum circuits, is both faithful and enjoys trainability guarantees.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Quantum generative models, in providing inherently efficient sampling strategies, show promise for achieving a near-term advantage on quantum hardware. Nonetheless, important questions remain regarding their scalability. In this work, we investigate the barriers to the trainability of quantum generative models posed by barren plateaus and exponential loss concentration. We explore the interplay between explicit and implicit models and losses, and show that using implicit generative models (such as quantum circuit-based models) with explicit losses (such as the KL divergence) leads to a new flavour of barren plateau. In contrast, the Maximum Mean Discrepancy (MMD), which is a popular example of an implicit loss, can be viewed as the expectation value of an observable that is either low-bodied and trainable, or global and untrainable depending on the choice of kernel. However, in parallel, we highlight that the low-bodied losses required for trainability cannot in general distinguish high-order correlations, leading to a fundamental tension between exponential concentration and the emergence of spurious minima. We further propose a new local quantum fidelity-type loss which, by leveraging quantum circuits to estimate the quality of the encoded distribution, is both faithful and enjoys trainability guarantees. Finally, we compare the performance of different loss functions for modelling real-world data from the High-Energy-Physics domain and confirm the trends predicted by our theoretical results.

Related papers

• Anticipating Decoherence: a Predictive Framework for Enhancing Coherence in Quantum Emitters [96.41185946460115]
  We develop an anticipatory framework for forecasting and decoherence engineering in remote quantum emitters.<n>We show that a machine learning model trained on limited data can accurately forecast unseen spectral behavior.<n>These results pave the way for real-time decoherence engineering in scalable quantum systems.
  arXiv  Detail & Related papers  (2025-08-04T17:23:14Z)
• Unitary Scrambling and Collapse: A Quantum Diffusion Framework for Generative Modeling [5.258882634977828]
  We propose QSC-Diffusion, the first fully quantum diffusion-based framework for image generation.<n>We employ parameterized quantum circuits with measurement-induced collapse for reverse denoising.<n>Remarkably, QSC-Diffusion achieves competitive FID scores across multiple datasets.
  arXiv  Detail & Related papers  (2025-06-12T11:00:21Z)
• 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 Latent Diffusion Models [65.16624577812436]
  We propose a potential version of a quantum diffusion model that leverages the established idea of classical latent diffusion models. This involves using a traditional autoencoder to reduce images, followed by operations with variational circuits in the latent space. The results demonstrate an advantage in using a quantum version, as evidenced by obtaining better metrics for the images generated by the quantum version.
  arXiv  Detail & Related papers  (2025-01-19T21:24:02Z)
• Estimates of loss function concentration in noisy parametrized quantum circuits [0.0]
  We introduce a new analytical formulation that enables precise calculation of the variance in deep quantum circuits. We show the emergence of a noise-induced absorption mechanism, a phenomenon that cannot arise in the purely reversible context of unitary quantum computing. Our framework applies to both unitary and non-unitary dynamics, allowing us to establish a deeper connection between the noise resilience of PQCs and the potential to enhance their expressive power.
  arXiv  Detail & Related papers  (2024-10-02T18:00:09Z)
• Unveiling the nonclassicality within quasi-distribution representations through deep learning [1.130790932059036]
  A widely adopted approach focuses on the negative values of a quasi-distribution representation as compelling evidence of nonclassicality. Here we propose a computational approach utilizing a deep generative model, processing three marginals, to construct the joint quasi-distribution functions. Our approach also provides a significant reduction of the experimental efforts of constructing the Wigner functions of quantum states.
  arXiv  Detail & Related papers  (2023-12-26T13:56:07Z)
• Gradients and frequency profiles of quantum re-uploading models [0.0]
  We prove bounds for the differences between gradients of the better-studied data-less parameterized quantum circuits and re-uploading models. For the expressivity, we prove that quantum re-uploading models output functions with vanishing high-frequency components and upper-bounded derivatives with respect to data.
  arXiv  Detail & Related papers  (2023-11-17T19:01:43Z)
• A PAC-Bayesian Perspective on the Interpolating Information Criterion [54.548058449535155]
  We show how a PAC-Bayes bound is obtained for a general class of models, characterizing factors which influence performance in the interpolating regime. We quantify how the test error for overparameterized models achieving effectively zero training error depends on the quality of the implicit regularization imposed by e.g. the combination of model, parameter-initialization scheme.
  arXiv  Detail & Related papers  (2023-11-13T01:48:08Z)
• Expressibility-induced Concentration of Quantum Neural Tangent Kernels [4.561685127984694]
  We study the connections between the trainability and expressibility of quantum tangent kernel models. For global loss functions, we rigorously prove that high expressibility of both the global and local quantum encodings can lead to exponential concentration of quantum tangent kernel values to zero. Our discoveries unveil a pivotal characteristic of quantum neural tangent kernels, offering valuable insights for the design of wide quantum variational circuit models.
  arXiv  Detail & Related papers  (2023-11-08T19:00:01Z)
• Tight and Efficient Gradient Bounds for Parameterized Quantum Circuits [7.0379869298557844]
  Training a parameterized model largely depends on the landscape of the underlying loss function. We show that these bounds, as well as the variance of the loss itself, can be estimated efficiently and classically-versa--providing practical tools to study the loss landscapes of VQA models. This insight has direct implications for hybrid Quantum Generative Adrial Networks (qGANs), a generative model that can be reformulated as a VQA with an observable composed of local and global terms.
  arXiv  Detail & Related papers  (2023-09-22T07:38:13Z)
• Quantum Generative Modeling using Parameterized Quantum Circuits [0.0]
  Quantum generative models use the intrinsic probabilistic nature of quantum mechanics to learn and reproduce complex probability distributions.<n>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.
  arXiv  Detail & Related papers  (2023-03-25T18:01:50Z)
• Model-Based Uncertainty in Value Functions [89.31922008981735]
  We focus on characterizing the variance over values induced by a distribution over MDPs. Previous work upper bounds the posterior variance over values by solving a so-called uncertainty Bellman equation. We propose a new uncertainty Bellman equation whose solution converges to the true posterior variance over values.
  arXiv  Detail & Related papers  (2023-02-24T09:18:27Z)
• Momentum Diminishes the Effect of Spectral Bias in Physics-Informed Neural Networks [72.09574528342732]
  Physics-informed neural network (PINN) algorithms have shown promising results in solving a wide range of problems involving partial differential equations (PDEs) They often fail to converge to desirable solutions when the target function contains high-frequency features, due to a phenomenon known as spectral bias. In the present work, we exploit neural tangent kernels (NTKs) to investigate the training dynamics of PINNs evolving under gradient descent with momentum (SGDM)
  arXiv  Detail & Related papers  (2022-06-29T19:03:10Z)
• ClusterQ: Semantic Feature Distribution Alignment for Data-Free Quantization [111.12063632743013]
  We propose a new and effective data-free quantization method termed ClusterQ. To obtain high inter-class separability of semantic features, we cluster and align the feature distribution statistics. We also incorporate the intra-class variance to solve class-wise mode collapse.
  arXiv  Detail & Related papers  (2022-04-30T06:58:56Z)
• Divergence Frontiers for Generative Models: Sample Complexity, Quantization Level, and Frontier Integral [58.434753643798224]
  Divergence frontiers have been proposed as an evaluation framework for generative models. We establish non-asymptotic bounds on the sample complexity of the plug-in estimator of divergence frontiers. We also augment the divergence frontier framework by investigating the statistical performance of smoothed distribution estimators.
  arXiv  Detail & Related papers  (2021-06-15T06:26:25Z)
• BayesIMP: Uncertainty Quantification for Causal Data Fusion [52.184885680729224]
  We study the causal data fusion problem, where datasets pertaining to multiple causal graphs are combined to estimate the average treatment effect of a target variable. We introduce a framework which combines ideas from probabilistic integration and kernel mean embeddings to represent interventional distributions in the reproducing kernel Hilbert space.
  arXiv  Detail & Related papers  (2021-06-07T10:14:18Z)

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.