Trainability of IQP Quantum Circuit Born Machines Under Gaussian Initialization

• URL: http://arxiv.org/abs/2606.10179v1
• Date: Mon, 08 Jun 2026 21:14:21 GMT
• Title: Trainability of IQP Quantum Circuit Born Machines Under Gaussian Initialization
• Abstract summary: Quantum Circuit Born Machines (QCBMs) offer a natural approach to generative machine learning by leveraging the Born rule.<n>Recent work has provided a method to classically train QCBMs with Instantaneous Quantum Polynomial (IQP) circuits via the Maximum Mean Discrepancy (MMD) loss.<n>It discusses strategies to either avoid or encourage exponential concentration, as well as the conditions under which barren plateaus are more likely to occur.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Fermi-Dirac machines as quantizations of neurons [51.809748057605184]
  We reinterpret Fermi-Dirac machines as canonical quantizations of classical neurons.<n>We develop efficient hybrid quantum-classical algorithms for evaluating outputs and gradients of our quantized neurons.<n> Numerical experiments indicate that neurons based on quantum Hamiltonians can learn functions that classical neurons cannot.
  arXiv  Detail & Related papers  (2026-05-23T04:09:03Z)
• IQP Born Machines under Data-dependent and Agnostic Initialization Strategies [0.0]
  Quantum circuit Born machines based on instantaneous quantum-time (IQP) circuits are natural candidates for quantum generative modeling.<n>Recent proposals focus on training IQP-QCBMs using Mean Maximum Discrepancy (MMD) losses built from low-body Pauli-$Z$ors.
  arXiv  Detail & Related papers  (2026-03-15T19:54:04Z)
• Characterizing Trainability of Instantaneous Quantum Polynomial Circuit Born Machines [7.716642023459826]
  Instantaneous quantum quantum circuit Born machines (IQP-QCBMs) have been proposed as quantum generative models.<n>We show that barren plateaus depend on the generator set and the spectrum of the chosen kernel.<n>We identify regimes in which low-weight-biased kernels avoid exponential suppression in structured topologies.
  arXiv  Detail & Related papers  (2026-02-11T17:12:56Z)
• The Born Ultimatum: Conditions for Classical Surrogation of Quantum Generative Models with Correlators [1.397434225914932]
  Quantum Circuit Born Machines (QCBMs) are powerful quantum generative models that sample according to the Born rule.<n>Recent train-classical, deploy-quantum approaches propose training classical surrogates of QCBMs and using quantum devices only for inference.<n>We analyze the limitations of these methods arising from deployment discrepancies between classically trained and quantumly deployed parameters.
  arXiv  Detail & Related papers  (2025-11-03T18:51:24Z)
• Calibration of Quantum Devices via Robust Statistical Methods [45.464983015777314]
  We numerically analyze advanced statistical methods for Bayesian inference against the state-of-the-art in quantum parameter learning.<n>We show advantages of these approaches over existing ones, namely under multi-modality and high dimensionality.<n>Our findings have applications in challenging quantumcharacterization tasks namely learning the dynamics of open quantum systems.
  arXiv  Detail & Related papers  (2025-07-09T15:22:17Z)
• Looking elsewhere: improving variational Monte Carlo gradients by importance sampling [41.94295877935867]
  Neural-network quantum states (NQS) offer a powerful and expressive ansatz for representing quantum many-body wave functions.<n>It is well known that some scenarios - such as sharply peaked wave functions emerging in quantum chemistry - lead to high-variance gradient estimators hindering the effectiveness of variational optimizations.<n>In this work we investigate a systematic strategy to tackle those sampling issues by means of adaptively tuned importance sampling.<n>Our approach can reduce the computational cost of vanilla VMC considerably, up to a factor of 100x when targeting highly peaked quantum chemistry wavefunctions.
  arXiv  Detail & Related papers  (2025-07-07T18:00:03Z)
• Practical Application of the Quantum Carleman Lattice Boltzmann Method in Industrial CFD Simulations [44.99833362998488]
  This work presents a practical numerical assessment of a hybrid quantum-classical approach to CFD based on the Lattice Boltzmann Method (LBM)<n>We evaluate this method on three benchmark cases featuring different boundary conditions, periodic, bounceback, and moving wall.<n>Our results confirm the validity of the approach, achieving median error fidelities on the order of $10-3$ and success probabilities sufficient for practical quantum state sampling.
  arXiv  Detail & Related papers  (2025-04-17T15:41:48Z)
• Discrete Randomized Smoothing Meets Quantum Computing [40.54768963869454]
  We show how to encode all the perturbations of the input binary data in superposition and use Quantum Amplitude Estimation (QAE) to obtain a quadratic reduction in the number of calls to the model. In addition, we propose a new binary threat model to allow for an extensive evaluation of our approach on images, graphs, and text.
  arXiv  Detail & Related papers  (2024-08-01T20:21:52Z)
• Wasserstein Quantum Monte Carlo: A Novel Approach for Solving the Quantum Many-Body Schr\"odinger Equation [56.9919517199927]
  "Wasserstein Quantum Monte Carlo" (WQMC) uses the gradient flow induced by the Wasserstein metric, rather than Fisher-Rao metric, and corresponds to transporting the probability mass, rather than teleporting it. We demonstrate empirically that the dynamics of WQMC results in faster convergence to the ground state of molecular systems.
  arXiv  Detail & Related papers  (2023-07-06T17:54:08Z)
• On the Sample Complexity of Quantum Boltzmann Machine Learning [0.0]
  We give an operational definition of QBM learning in terms of the difference in expectation values between the model and target.<n>We prove that a solution can be obtained with gradient descent using at most a number of Gibbs states.<n>In particular, we give pre-training strategies based on mean-field, Gaussian Fermionic, and geometrically local Hamiltonians.
  arXiv  Detail & Related papers  (2023-06-26T18:00:50Z)
• Protocols for classically training quantum generative models on probability distributions [17.857341127079305]
  Quantum Generative Modelling (QGM) relies on preparing quantum states and generating samples as hidden - or known - probability distributions. We propose protocols for classical training of QGMs based on circuits of the specific type that admit an efficient gradient. We numerically demonstrate the end-to-end training of IQP circuits using probability distributions for up to 30 qubits on a regular desktop computer.
  arXiv  Detail & Related papers  (2022-10-24T17:57:09Z)
• Theory of Quantum Generative Learning Models with Maximum Mean Discrepancy [67.02951777522547]
  We study learnability of quantum circuit Born machines (QCBMs) and quantum generative adversarial networks (QGANs) We first analyze the generalization ability of QCBMs and identify their superiorities when the quantum devices can directly access the target distribution. Next, we prove how the generalization error bound of QGANs depends on the employed Ansatz, the number of qudits, and input states.
  arXiv  Detail & Related papers  (2022-05-10T08:05:59Z)
• Error mitigation and quantum-assisted simulation in the error corrected regime [77.34726150561087]
  A standard approach to quantum computing is based on the idea of promoting a classically simulable and fault-tolerant set of operations. We show how the addition of noisy magic resources allows one to boost classical quasiprobability simulations of a quantum circuit.
  arXiv  Detail & Related papers  (2021-03-12T20:58:41Z)

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.