Classical Limits of Spectral Filtering in Quantum Generative Models

• URL: http://arxiv.org/abs/2608.14169v1
• Date: Fri, 14 Aug 2026 10:29:09 GMT
• Title: Classical Limits of Spectral Filtering in Quantum Generative Models
• Abstract summary: diagonal filter suppresses the high frequencies associated with finite-sample noise.<n>We examine whether this coherent operation produces anything that classical post-processing of samples from the unfiltered model cannot match.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Spectral filtering has been proposed as a route to regularization in quantum generative models: the quantum Fourier transform exposes the amplitude spectrum of a quantum circuit Born machine, and a diagonal filter suppresses the high frequencies associated with finite-sample noise, an operation whose classical counterpart seemingly requires manipulating an exponentially long amplitude vector. We examine whether this coherent operation produces anything that classical post-processing of samples from the unfiltered model cannot match. Measuring the filter against convolution with a symmetric probability kernel at matched sampling cost, which accounts for the post-selection overhead of attenuation, we derive necessary and sufficient conditions for the gap between the two to vanish. Magnitude (attenuating) filters obey a dichotomy: at a fixed affordability threshold, the filtered output is either a constant-size Fourier object with an efficient classical sampler, or the passband must widen until no fixed frequency is attenuated and the filter no longer smooths. In neither case does the filter create a quantum-classical separation. Whatever separation survives is inherited from the spectral phase of the input state. Numerical experiments on trained circuit Born machines confirm the classification and show that the deciding phases are invisible to the Born-rule training loss and set by the initialization. Within the diagonal family, pure phase filters remain the only spectral operations exempt from these constraints.

Related papers

• A Quantum-Inspired Dequantization Method for Diagonally Weighted Matrix Functions: Application to Learning with Optimized Random Features [0.9558392439655014]
  We develop a classical algorithm to address this type of quantum-advantage candidate.<n>Applying this method dequantizes the sampler for optimized random features, giving a classical sampler with prescribed accuracy and runtime.
  arXiv  Detail & Related papers  (2026-09-09T18:23:55Z)
• Deformable Wiener Filter for Future Video Coding [55.405068056883614]
  We propose a deformable Wiener Filter (DWF) for in-loop filters in Versatile Video Coding (VVC)<n>It combines the local and non-local characteristics and supervisedly trains the filter coefficients based on the Wiener Filter theory.<n>It achieves 1.16%, 1.92%, and 2.67% bit-rate savings on average compared to the VTM-11.0 for All Intra, Random Access, and Low-Delay B configurations.
  arXiv  Detail & Related papers  (2026-06-01T02:24:07Z)
• Quantum phase estimation based filtering: performance analysis and application to low-energy spectral calculation [0.28745038175377646]
  We analyze the performance of filters based on the quantum phase estimation (QPE) algorithm.<n>We show that when the conventional rectangular window function is used for the QPE input state, the resulting filter exhibits an oscillating behavior known as the Gibbs phenomenon.<n>We also study a two-step algorithm for low-energy spectral simulations, composed of a coarse grid for filtering and a fine grid for obtaining final high-resolution spectra.
  arXiv  Detail & Related papers  (2025-07-02T04:57:33Z)
• Entanglement, Squeezing and non-Locality in Filtered Two-Mode Squeezed Mixed States [0.0]
  We investigate the entanglement and non-locality between specific spectral components of continuous variable two-mode squeezed mixed states. We provide precise boundaries for entanglement and non-locality. We also evaluate the squeezing of two-mode hybrid quadrature as a measure of entanglement.
  arXiv  Detail & Related papers  (2024-06-11T17:57:35Z)
• Closed-form Filtering for Non-linear Systems [83.91296397912218]
  We propose a new class of filters based on Gaussian PSD Models, which offer several advantages in terms of density approximation and computational efficiency. We show that filtering can be efficiently performed in closed form when transitions and observations are Gaussian PSD Models. Our proposed estimator enjoys strong theoretical guarantees, with estimation error that depends on the quality of the approximation and is adaptive to the regularity of the transition probabilities.
  arXiv  Detail & Related papers  (2024-02-15T08:51:49Z)
• Suppressing Amplitude Damping in Trapped Ions: Discrete Weak Measurements for a Non-unitary Probabilistic Noise Filter [62.997667081978825]
  We introduce a low-overhead protocol to reverse this degradation. We present two trapped-ion schemes for the implementation of a non-unitary probabilistic filter against amplitude damping noise. This filter can be understood as a protocol for single-copy quasi-distillation.
  arXiv  Detail & Related papers  (2022-09-06T18:18:41Z)
• Filter functions for the Glauber-Sudarshan $P$-function regularization [0.0]
  We study filter functions that are introduced to regularize the Glauber-Sudarshan $P$ function. We show that the quantum map associated with a filter function is completely positive and trace preserving. We propose applications of our results for estimating the output state of an unknown quantum process.
  arXiv  Detail & Related papers  (2022-06-11T19:29:22Z)
• Computational Doob's h-transforms for Online Filtering of Discretely Observed Diffusions [65.74069050283998]
  We propose a computational framework to approximate Doob's $h$-transforms. The proposed approach can be orders of magnitude more efficient than state-of-the-art particle filters.
  arXiv  Detail & Related papers  (2022-06-07T15:03:05Z)
• Quantum Gaussian filter for exploring ground-state properties [0.0]
  Filter methods realize a projection from a superposed quantum state onto a target state, which can be efficient if two states have sufficient overlap. We propose a quantum Gaussian filter (QGF) with the filter operator being a Gaussian function of the system Hamiltonian. A hybrid quantum-classical algorithm feasible on near-term quantum computers is developed.
  arXiv  Detail & Related papers  (2021-12-11T16:55:13Z)
• Quantum Error Mitigation Relying on Permutation Filtering [84.66087478797475]
  We propose a general framework termed as permutation filters, which includes the existing permutation-based methods as special cases. We show that the proposed filter design algorithm always converges to the global optimum, and that the optimal filters can provide substantial improvements over the existing permutation-based methods.
  arXiv  Detail & Related papers  (2021-07-03T16:07:30Z)
• Machine learning-based conditional mean filter: a generalization of the ensemble Kalman filter for nonlinear data assimilation [42.60602838972598]
  We propose a machine learning-based ensemble conditional mean filter (ML-EnCMF) for tracking possibly high-dimensional non-Gaussian state models with nonlinear dynamics based on sparse observations. The proposed filtering method is developed based on the conditional expectation and numerically implemented using machine learning (ML) techniques combined with the ensemble method.
  arXiv  Detail & Related papers  (2021-06-15T06:40:32Z)
• Gaussian versus non-Gaussian filtering of phase-insensitive nonclassicality [0.0]
  bosonic phase-space functions are compared with their ability to uncover nonclassical effects of light through their negativities. We show that significant negativities of non-Gaussian filtered quasiprobabilities uncover nonclassical effects even for low efficiencies.
  arXiv  Detail & Related papers  (2020-10-05T17:20:32Z)

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.