Measurement-induced overconcentration in quantum generative models

• URL: http://arxiv.org/abs/2607.10055v1
• Date: Sat, 11 Jul 2026 00:50:14 GMT
• Title: Measurement-induced overconcentration in quantum generative models
• Abstract summary: We introduce three complementary metrics: accuracy, generative power, and input sensitivity.<n>For Haar-random monitored circuits, we prove that one-step models retain input sensitivity up to dimension-suppressed corrections.<n>We propose a truncated quantum denoising diffusion probabilistic model (QuDDPM), which restricts the temporal depth of both the forward diffusion and reverse denoising processes.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Quantum measurement is a key resource for quantum generative learning, providing intrinsic stochasticity for generating diverse quantum samples. However, in measurement-assisted state-ensemble resampling, repeated measurements can also induce overconcentration: under a fixed measurement trajectory, distinct input states progressively converge toward similar output states, suppressing input-dependent diversity. To diagnose this effect, we introduce three complementary metrics: accuracy, generative power, and input sensitivity. For Haar-random monitored circuits, we prove that one-step models retain input sensitivity up to dimension-suppressed corrections, whereas sequential monitored circuits exhibit a depth-dependent loss of input sensitivity. Motivated by this diagnosis, we propose a truncated quantum denoising diffusion probabilistic model (QuDDPM), which restricts the temporal depth of both the forward diffusion and reverse denoising processes. Numerical benchmarks show that truncated QuDDPM preserves stronger input sensitivity while maintaining accuracy and generative power comparable to the original model. These results identify measurement-induced overconcentration as a dynamical limitation of deep monitored quantum generative models and establish temporal depth as a design parameter for balancing measurement-induced randomness with input-dependent diversity.

Related papers

• Mitigating Measurement-Induced Training Instability in Hybrid Quantum Neural Networks for Protein Classification [0.0]
  We introduce a learnable scaling parameter, Quantum Measurement Temperature (QMT), which rescales quantum measurement outputs prior to the loss.<n>QMT acts during training and compensates for the physically imposed bounds on quantum measurement outputs.<n>Results demonstrate that QMT enables stable and reliable training of hybrid QNNs for practical applications.
  arXiv  Detail & Related papers  (2026-06-21T15:10:51Z)
• Optimal multiparameter quantum estimation in accelerating Unruh-DeWitt detectors [0.09236074230806578]
  We investigate the ultimate precision limits for relativistic quantum thermometry in a bipartite system of uniformly accelerated detectors.<n>We show that dissipative noise results in more significant precision loss than purely dephasing mechanisms.
  arXiv  Detail & Related papers  (2026-03-08T01:35:45Z)
• Squeezed-Light-Enhanced Multiparameter Quantum Estimation in Cavity Magnonics [0.0]
  We propose an experimentally realistic scheme to improve the precision of simultaneously estimating different parameters in a cavity-magnon system.<n>We show that when nonlinearity is introduced into the system, quantum noise is significantly suppressed.
  arXiv  Detail & Related papers  (2026-01-20T10:13:59Z)
• Mitigating Barren plateaus in quantum denoising diffusion probabilistic models [49.90716699848553]
  Quantum generative models leverage quantum superposition and entanglement to enhance learning efficiency for both classical and quantum data.<n>QuDDPM has been proposed as a promising framework for quantum generative learning.<n>We show that barren plateaus emerge in QuDDPMs due to the use of 2-design states as the input for the denoising process.<n>We introduce an improved QuDDPM that utilizes a distribution maintaining a certain distance from the Haar distribution, ensuring better trainability.
  arXiv  Detail & Related papers  (2025-12-07T07:01:44Z)
• Regulating Model Reliance on Non-Robust Features by Smoothing Input Marginal Density [93.32594873253534]
  Trustworthy machine learning requires meticulous regulation of model reliance on non-robust features. We propose a framework to delineate and regulate such features by attributing model predictions to the input.
  arXiv  Detail & Related papers  (2024-07-05T09:16:56Z)
• A Quantum Neural Network-Based Approach to Power Quality Disturbances Detection and Recognition [15.789631792979366]
  Power quality disturbances (PQDs) significantly impact the stability and reliability of power systems. This paper proposes an improved quantum neural networks (QNN) model for PQDs detection and recognition. The model achieves accuracies of 99.75%, 97.85% and 95.5% in experiments involving the detection of disturbances, recognition of seven single disturbances, and recognition of ten mixed disturbances.
  arXiv  Detail & Related papers  (2024-06-05T09:10:11Z)
• Quantum Conformal Prediction for Reliable Uncertainty Quantification in Quantum Machine Learning [47.991114317813555]
  Quantum models implement implicit probabilistic predictors that produce multiple random decisions for each input through measurement shots. This paper proposes to leverage such randomness to define prediction sets for both classification and regression that provably capture the uncertainty of the model.
  arXiv  Detail & Related papers  (2023-04-06T22:05:21Z)
• Analyzing and Unifying Robustness Measures for Excitation Transfer Control in Spin Networks [0.0]
  We investigate the correlation between the log-sensitivity and the RIM for evaluating the robustness of single excitation transfer fidelity in spin chains and rings. We show that the expected differential sensitivity of the error agrees with the differential sensitivity of the RIM, where the expectation is over the error probability distribution.
  arXiv  Detail & Related papers  (2023-03-16T17:34:54Z)
• 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)
• Monotonicity and Double Descent in Uncertainty Estimation with Gaussian Processes [52.92110730286403]
  It is commonly believed that the marginal likelihood should be reminiscent of cross-validation metrics and that both should deteriorate with larger input dimensions. We prove that by tuning hyper parameters, the performance, as measured by the marginal likelihood, improves monotonically with the input dimension. We also prove that cross-validation metrics exhibit qualitatively different behavior that is characteristic of double descent.
  arXiv  Detail & Related papers  (2022-10-14T08:09:33Z)
• Continuous-time dynamics and error scaling of noisy highly-entangling quantum circuits [58.720142291102135]
  We simulate a noisy quantum Fourier transform processor with up to 21 qubits. We take into account microscopic dissipative processes rather than relying on digital error models. We show that depending on the dissipative mechanisms at play, the choice of input state has a strong impact on the performance of the quantum algorithm.
  arXiv  Detail & Related papers  (2021-02-08T14:55:44Z)

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.