Mitigating Frequency Learning Bias in Quantum Models via Multi-Stage Residual Learning

• URL: http://arxiv.org/abs/2603.10083v1
• Date: Tue, 10 Mar 2026 11:18:20 GMT
• Title: Mitigating Frequency Learning Bias in Quantum Models via Multi-Stage Residual Learning
• Abstract summary: Quantum machine learning models often struggle to learn functions with multiple frequency components.<n>We adapt the multi-stage residual learning idea to the quantum domain, iteratively training additional quantum modules on the residuals of previous stages.<n>Our work provides a practical framework for enhancing the spectral expressivity of quantum models.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Quantum machine learning models based on parameterized circuits can be viewed as Fourier series approximators. However, they often struggle to learn functions with multiple frequency components, particularly high-frequency or non-dominant ones; a phenomenon we term the quantum Fourier parameterization bias. Inspired by recent advances in classical Fourier neural operators (FNOs), we adapt the multi-stage residual learning idea to the quantum domain, iteratively training additional quantum modules on the residuals of previous stages. We evaluate our method on a synthetic benchmark composed of spatially localized frequency components with diverse envelope shapes (Gaussian, Lorentzian, triangular). Systematic experiments show that the number of qubits, the encoding scheme, and residual learning are all crucial for resolving multiple frequencies; residual learning alone can improve test MSE significantly over a single-stage baseline trained for the same total number of epochs. Our work provides a practical framework for enhancing the spectral expressivity of quantum models and offers new insights into their frequency-learning behavior.

Related papers

• Bernstein-Vazirani Networks: Quantum Machine Learning by Interference [57.703235450585595]
  Bernstein-Vazirani Networks (BVNs) is a non-variational quantum machine learning framework.<n>BVNs leverage quantum interference for supervised learning, demonstrated on vision and representation learning tasks.
  arXiv  Detail & Related papers  (2026-08-19T15:35:37Z)
• Hybrid Classical-Quantum Transfer Learning with Noisy Quantum Circuits [0.0]
  We introduce a family of compact quantum transfer learning architectures for image classification.<n>We instantiate and evaluate several classical-quantum hybrid models implemented in PennyLane and Qiskit.<n> Experimental results show that the proposed quantum transfer learning architectures achieve competitive and, in several cases, superior accuracy.
  arXiv  Detail & Related papers  (2026-03-17T12:28:33Z)
• A Unified Frequency Principle for Quantum and Classical Machine Learning [9.529771617722703]
  We present a unified theoretical framework for the frequency principle (F-principle) that characterizes the training dynamics of quantum neural networks.<n>Within this framework, we prove that quantum neural networks exhibit a spectral bias toward learning low-frequency components of target functions.<n>Our results provide a frequency-domain lens that unifies classical and quantum learning dynamics, clarifies the role of noise in shaping trainability, and guides the design of noise-resilient quantum neural networks.
  arXiv  Detail & Related papers  (2026-01-06T16:44:22Z)
• Quantum Visual Fields with Neural Amplitude Encoding [70.86293548779774]
  We introduce a new type of Quantum Implicit Neural Representation (QINR) for 2D image and 3D geometric field learning.<n>QVF encodes classical data into quantum statevectors using neural amplitude encoding grounded in a learnable energy manifold.<n>Our ansatz follows a fully entangled design of learnable parametrised quantum circuits, with quantum (unitary) operations performed in the real Hilbert space.
  arXiv  Detail & Related papers  (2025-08-14T17:59:52Z)
• Mitigating Exponential Mixed Frequency Growth through Frequency Selection [3.243345719637229]
  Angle encoding has emerged as a popular choice as feature map (FM) for embedding classical data into quantum models.<n>We show that training failures can occur even when all relevant frequencies are theoretically accessible.<n>We introduce frequency selection as a practical solution that reduces parameter requirements.
  arXiv  Detail & Related papers  (2025-08-14T11:10:07Z)
• Non-perturbative switching rates in bistable open quantum systems: from driven Kerr oscillators to dissipative cat qubits [72.41778531863143]
  We use path integral techniques to predict the switching rate in a single-mode bistable open quantum system.<n>Our results open new avenues for exploring switching phenomena in multistable single- and many-body open quantum systems.
  arXiv  Detail & Related papers  (2025-07-24T18:01:36Z)
• Spectral Bias in Variational Quantum Machine Learning [0.0]
  We study the effect specifically in parameterised quantum circuits (PQCs)<n>We find that the magnitude of the Fourier coefficients' gradients during training strongly correlates with the coefficients' redundancy.<n>We also demonstrate that PQCs with greater redundancy exhibit increased robustness to random perturbations in their parameters at the corresponding frequencies.
  arXiv  Detail & Related papers  (2025-06-27T18:11:54Z)
• VQC-MLPNet: An Unconventional Hybrid Quantum-Classical Architecture for Scalable and Robust Quantum Machine Learning [50.95799256262098]
  Variational quantum circuits (VQCs) hold promise for quantum machine learning but face challenges in expressivity, trainability, and noise resilience.<n>We propose VQC-MLPNet, a hybrid architecture where a VQC generates the first-layer weights of a classical multilayer perceptron during training, while inference is performed entirely classically.
  arXiv  Detail & Related papers  (2025-06-12T01:38:15Z)
• Frequency principle for quantum machine learning via Fourier analysis [0.6138671548064356]
  We propose a frequency principle for parameterized quantum circuits that preferentially train frequencies within the primary frequency range.<n>Our work suggests a new avenue for understanding quantum advantage from the training process.
  arXiv  Detail & Related papers  (2024-09-10T17:49:09Z)
• Fourier Neural Operators for Learning Dynamics in Quantum Spin Systems [77.88054335119074]
  We use FNOs to model the evolution of random quantum spin systems. We apply FNOs to a compact set of Hamiltonian observables instead of the entire $2n$ quantum wavefunction.
  arXiv  Detail & Related papers  (2024-09-05T07:18:09Z)
• Efficient Learning for Linear Properties of Bounded-Gate Quantum Circuits [62.46800898243033]
  Recent progress in quantum learning theory prompts a question: can linear properties of a large-qubit circuit be efficiently learned from measurement data generated by varying classical inputs?<n>We prove that the sample complexity scaling linearly in $d$ is required to achieve a small prediction error, while the corresponding computational complexity may scale exponentially in d.<n>We propose a kernel-based method leveraging classical shadows and truncated trigonometric expansions, enabling a controllable trade-off between prediction accuracy and computational overhead.
  arXiv  Detail & Related papers  (2024-08-22T08:21:28Z)
• Let Quantum Neural Networks Choose Their Own Frequencies [0.0]
  We generalize quantum models to include a set of trainable parameters in the generator, leading to a trainable frequency (TF) quantum model. We numerically demonstrate how TF models can learn generators with desirable properties for solving the task at hand.
  arXiv  Detail & Related papers  (2023-09-06T18:00:07Z)
• Incremental Spatial and Spectral Learning of Neural Operators for Solving Large-Scale PDEs [86.35471039808023]
  We introduce the Incremental Fourier Neural Operator (iFNO), which progressively increases the number of frequency modes used by the model. We show that iFNO reduces total training time while maintaining or improving generalization performance across various datasets. Our method demonstrates a 10% lower testing error, using 20% fewer frequency modes compared to the existing Fourier Neural Operator, while also achieving a 30% faster training.
  arXiv  Detail & Related papers  (2022-11-28T09:57:15Z)

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.