The ZZ feature map induces a signless Laplacian metric: a closed-form classical surrogate for quantum kernel regression

• URL: http://arxiv.org/abs/2608.29422v1
• Date: Sat, 29 Aug 2026 19:59:00 GMT
• Title: The ZZ feature map induces a signless Laplacian metric: a closed-form classical surrogate for quantum kernel regression
• Abstract summary: We prove that in the small-bandwidth regime the induced kernel is, to leading order, an anisotropic Gaussian kernel with metric M = I + pi2 Q.<n>The corresponding classical kernel requires no fitted parameters and no quantum simulation.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Quantum kernel methods lose their advantage over classical kernels once the encoding bandwidth is tuned, and bandwidth-tuned quantum kernels have been shown to resemble radial basis function kernels closely. The analytical support for that observation rests on separable encoding circuits and captures entangling circuits only qualitatively. We close this gap for the ZZ feature map. We prove that in the small-bandwidth regime the induced kernel is, to leading order, an anisotropic Gaussian kernel with metric M = I + pi^2 Q, where Q is the signless Laplacian of the entanglement graph, and that the quadratic structure persists at every circuit depth as a pullback of the Fubini-Study metric. The anisotropy depends entirely on a phase convention: under the unshifted convention the metric is the identity irrespective of entanglement, which explains the isotropic resemblance previously reported. The derivation is verified against direct simulation for path, cycle and complete entanglement graphs, with relative error below 10^-3. The corresponding classical kernel requires no fitted parameters and no quantum simulation. Compared with the quantum kernel across two near-infrared spectroscopic benchmarks, four targets, five preprocessing pipelines and 100 resampled splits per cell, the paired 95% bootstrap interval contains zero in 18 of 20 cells, the typical relative difference in test error is 2.7%, and the two families select the same preprocessing pipeline in 96% of splits. The regime in which the reduction fails begins at the same bandwidth on both datasets and adds no robust predictive value: restricting the grid to the classical regime improves mean test error by 3.8%, a gain that an equally large random restriction does not reproduce. The quantum circuit can thus be removed without detectable predictive loss, and we can state precisely which classical kernel it was computing.

Related papers

• Active Quantum Kernel Acquisition for Gaussian Process Regression [30.032230630492155]
  Recent work on quantum kernel classification has shown that allocating shots non-uniformly across kernel entries can reduce the shot budget required to reach a target accuracy.<n>We extend this idea to Gaussian process (GP) regression, a setting whose downstream quantities (full-spectrum posterior variance, log-determinant, marginal likelihood) couple to kernel error more tightly than the sign-only outputs of classification.<n>We derive three closed-form pair-level sensitivities predictive coupling $|_i_j|$, leave-one-out residual, and marginal-likelihood gradient and plug them into a Neyman-style minimum
  arXiv  Detail & Related papers  (2026-06-27T09:40:20Z)
• Spectral Anatomy of Quantum Gaussian Process Kernels [38.264196157340216]
  We prove a Cauchy-Schwarz tail bound on Nystrm approximation error, a finite-sample variance-contraction identity, and a characterization of the emphtarget-dependent optimal entropy.<n>The diagnostic is kernel-agnostic: hardware-efficient, matchgate, IQP emphand RBF/Matérn/RFF/deep- kernel families all collapse onto identical $S/log n$ curves.
  arXiv  Detail & Related papers  (2026-05-29T07:41:14Z)
• Q-SINDy: Quantum-Kernel Sparse Identification of Nonlinear Dynamics with Provable Coefficient Debiasing [1.4323566945483497]
  Quantum feature maps offer expressive embeddings for classical learning tasks.<n>We introduce textbfQ-SINDy, a quantum kernelaugmented SINDy framework.<n>We identify a specific failure mode that arises: emphcoefficient cannibalization, in which quantum features absorb mass coefficient that rightfully belongs to the basis, corrupting equation recovery.
  arXiv  Detail & Related papers  (2026-04-18T02:00:27Z)
• Finite-size resource scaling for learning quantum phase transitions with fidelity-based support vector machines [0.0]
  We quantify the measurement resources required to estimate fidelity-based quantum kernels for many-body ground states.<n>We show that increasing symmetry in the underlying spin model systematically amplifies shot requirements.<n>Our symmetry-aware bounds provide a pragmatic procedure for physics-informed quantum machine learning.
  arXiv  Detail & Related papers  (2026-03-18T18:59:57Z)
• Benchmarking of quantum fidelity kernels for Gaussian process regression [1.7287035469433212]
  Quantum computing algorithms have been shown to produce performant quantum kernels for machine-learning classification problems. We show that quantum kernels can achieve the same, though not better, expressivity as classical kernels for regression problems.
  arXiv  Detail & Related papers  (2024-07-22T18:19:48Z)
• KPZ scaling from the Krylov space [83.88591755871734]
  Recently, a superdiffusion exhibiting the Kardar-Parisi-Zhang scaling in late-time correlators and autocorrelators has been reported. Inspired by these results, we explore the KPZ scaling in correlation functions using their realization in the Krylov operator basis.
  arXiv  Detail & Related papers  (2024-06-04T20:57:59Z)
• Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks [54.177130905659155]
  Recent studies show that a reproducing kernel Hilbert space (RKHS) is not a suitable space to model functions by neural networks. In this paper, we study a suitable function space for over- parameterized two-layer neural networks with bounded norms.
  arXiv  Detail & Related papers  (2024-04-29T15:04:07Z)
• Qubit recycling and the path counting problem [0.0]
  Recently, it was shown that the qudits used in circuits of a convolutional form (e.g., Matrix Product State sand Multi-scaleanglement Renormalization Ansatz) can be reset unitarily. We analyze the fidelity of this protocol for a family of quantum circuits that interpolates between such circuits and local quantum circuits.
  arXiv  Detail & Related papers  (2023-01-09T23:59:41Z)
• Unimon qubit [42.83899285555746]
  Superconducting qubits are one of the most promising candidates to implement quantum computers. Here, we introduce and demonstrate a superconducting-qubit type, the unimon, which combines the desired properties of high non-linearity, full insensitivity to dc charge noise, insensitivity to flux noise, and a simple structure consisting only of a single Josephson junction in a resonator.
  arXiv  Detail & Related papers  (2022-03-11T12:57:43Z)
• Optimal policy evaluation using kernel-based temporal difference methods [78.83926562536791]
  We use kernel Hilbert spaces for estimating the value function of an infinite-horizon discounted Markov reward process. We derive a non-asymptotic upper bound on the error with explicit dependence on the eigenvalues of the associated kernel operator. We prove minimax lower bounds over sub-classes of MRPs.
  arXiv  Detail & Related papers  (2021-09-24T14:48:20Z)
• Random quantum circuits anti-concentrate in log depth [118.18170052022323]
  We study the number of gates needed for the distribution over measurement outcomes for typical circuit instances to be anti-concentrated. Our definition of anti-concentration is that the expected collision probability is only a constant factor larger than if the distribution were uniform. In both the case where the gates are nearest-neighbor on a 1D ring and the case where gates are long-range, we show $O(n log(n)) gates are also sufficient.
  arXiv  Detail & Related papers  (2020-11-24T18:44:57Z)

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.