Circuit Harmonic Matrices: A Spectral Framework for Quantum Machine Learning

• URL: http://arxiv.org/abs/2604.04292v1
• Date: Sun, 05 Apr 2026 22:22:56 GMT
• Title: Circuit Harmonic Matrices: A Spectral Framework for Quantum Machine Learning
• Abstract summary: We introduce a data-agnostic framework that maps a broad family of circuits into a single architecture matrix built over learnable features and parameters.<n>We show how correlations between learnable features arise from shared parameter-induced harmonics generated by non-commuting gate-observable interactions.<n>The resulting framework makes circuit-induced structure explicit, separating architectural effects from data-dependent ones.
• Score: 0.03823356975862006
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Parametrised quantum circuits are a central framework for near term quantum machine learning. However, it remains challenging to determine in advance how architectural choices, such as encoding strategies, gate placement, and entangling structure, influence both the expressive capacity of the model and its trainability during optimisation. We introduce a data-agnostic framework, one requiring no knowledge of a training dataset or optimisation trajectory, that maps a broad family of circuits into a single architecture matrix built over learnable features and parameters. We show that this framework provides an explicit link between circuit structure, the correlations among learnable features, and the geometry of training kernels through the factorisation of each of these objects as quadratic forms in terms of these matrices. We show how correlations between learnable features arise from shared parameter-induced harmonics generated by non-commuting gate-observable interactions during Heisenberg back-propagation, and how these correlations are encoded directly in the architecture matrix. From this perspective, kernel structure and coefficient statistics can be reconstructed analytically from circuit design alone, without reference to a dataset or optimisation trajectory. The resulting framework makes circuit-induced structure explicit, separating architectural effects from data-dependent ones, and provides a principled foundation for analysing and comparing parametrised quantum circuits based on intrinsic, design-level signatures.

Related papers

• Learning Hidden Structures in Open Quantum Dynamics [78.4675086615913]
  We introduce a machine-learning approach for identifying hidden structural features of open quantum dynamics under restricted experimental access.<n>Our framework targets the inference of invariant algebraic structures underlying the effective Markovian evolution.<n>The feasibility of the approach is illustrated on multiple synthetic models and a waveguide quantum electrodynamics system.
  arXiv  Detail & Related papers  (2026-04-01T10:20:38Z)
• Regression of Functions by Quantum Neural Networks Circuits [41.09105068326236]
  This work investigates automated quantum-circuit construction for regression tasks.<n>It introduces a genetic-algorithm framework that discovers Reduced Regressor QNN architectures.
  arXiv  Detail & Related papers  (2025-12-23T01:58:03Z)
• Topology Identification and Inference over Graphs [61.06365536861156]
  Topology identification and inference of processes evolving over graphs arise in timely applications involving brain, transportation, financial, power, as well as social and information networks.<n>This chapter provides an overview of graph topology identification and statistical inference methods for multidimensional data.
  arXiv  Detail & Related papers  (2025-12-11T00:47:09Z)
• From Coefficients to Directions: Rethinking Model Merging with Directional Alignment [66.99062575537555]
  We introduce a unified geometric framework, emphMerging with Directional Alignment (method), which aligns directional structures consistently in both the parameter and feature spaces.<n>Our analysis shows that directional alignment improves structural coherence, and extensive experiments across benchmarks, model scales, and task configurations further validate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2025-11-29T08:40:58Z)
• Generalized Linear Mode Connectivity for Transformers [87.32299363530996]
  A striking phenomenon is linear mode connectivity (LMC), where independently trained models can be connected by low- or zero-loss paths.<n>Prior work has predominantly focused on neuron re-ordering through permutations, but such approaches are limited in scope.<n>We introduce a unified framework that captures four symmetry classes: permutations, semi-permutations, transformations, and general invertible maps.<n>This generalization enables, for the first time, the discovery of low- and zero-barrier linear paths between independently trained Vision Transformers and GPT-2 models.
  arXiv  Detail & Related papers  (2025-06-28T01:46:36Z)
• Circuit Design based on Feature Similarity for Quantum Generative Modeling [0.6954287924634025]
  We propose a metric-based extension to design an extended circuit based on a similarity measured between the dataset features.<n>Our results show that the metric-based extension offers the means to introduce inductive bias while designing a circuit under limited resources.
  arXiv  Detail & Related papers  (2025-03-15T03:45:22Z)
• Induced Covariance for Causal Discovery in Linear Sparse Structures [55.2480439325792]
  Causal models seek to unravel the cause-effect relationships among variables from observed data. This paper introduces a novel causal discovery algorithm designed for settings in which variables exhibit linearly sparse relationships.
  arXiv  Detail & Related papers  (2024-10-02T04:01:38Z)
• Profiling quantum circuits for their efficient execution on single- and multi-core architectures [1.7340157845783293]
  This study introduces graph theory-based metrics extracted from their qubit interaction graph and gate dependency graph. It uncovers a connection between parameters rooted in both qubit interaction and gate dependency graphs, and the performance metrics for quantum circuit mapping.
  arXiv  Detail & Related papers  (2024-07-17T15:08:50Z)
• Approximation Theory of Convolutional Architectures for Time Series Modelling [15.42770933459534]
  We study the approximation properties of convolutional architectures applied to time series modelling. Recent results reveal an intricate connection between approximation efficiency and memory structures in the data generation process.
  arXiv  Detail & Related papers  (2021-07-20T09:19:26Z)
• Quantum Circuit Design Search [0.0]
  This article explores search strategies for the design of parameterized quantum circuits. We propose several optimization approaches including random search plus survival of the fittest. We introduce nontrivial circuit architectures that are arduous to be hand-designed and efficient in terms of trainability.
  arXiv  Detail & Related papers  (2020-12-07T20:41:57Z)
• Inter-layer Transition in Neural Architecture Search [89.00449751022771]
  The dependency between the architecture weights of connected edges is explicitly modeled in this paper. Experiments on five benchmarks confirm the value of modeling inter-layer dependency and demonstrate the proposed method outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-11-30T03:33:52Z)

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.