paper-with-me

홈 › Papers

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

2026-03-10 · Ammar Daskin arxiv

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.

📄 PDF Abstract BibTeX arXiv:2603.10083

Code (0)

등록된 구현이 없습니다.

Tasks

Quantum Machine Learning

Similar Papers 제목 키워드 기반

On the study of frequency control and spectral bias in Wavelet-Based Kolmogorov Arnold networks: A path to physics-informed KANs

2025-02-01 · Juan Daniel Meshir, Abel Palafox, Edgar Alejandro Guerrero

Spectral bias, the tendency of neural networks to prioritize learning low-frequency components of functions during the initial training stages, poses a significant challenge when approximating solutions with high-frequen…

Kolmogorov-Arnold Networks

FSGR: Mitigating Token Frequency Bias for Fair SID-Based Generative Recommendation

2026-08-13 · Yuchen Zheng, Sihan Xu, Jingwen Yang, Xiangrui Cai 외 arxiv

Semantic ID (SID)-based generative recommendation has recently achieved remarkable success. However, existing methods suffer from a previously overlooked fairness issue, which we term \textbf{Token Frequency Bias}, where…

Quantum Implicit Neural Representations for 3D Scene Reconstruction and Novel View Synthesis

2025-12-14 · Yeray Cordero, Paula García-Molina, Fernando Vilariño arxiv

Implicit neural representations (INRs) have become a powerful paradigm for continuous signal modeling and 3D scene reconstruction, yet classical networks suffer from a well-known spectral bias that limits their ability t…

Novel View Synthesis

Mitigating Spectral Bias in Neural Operators via High-Frequency Scaling for Physical Systems

2025-03-17 · Siavash Khodakarami, Vivek Oommen, Aniruddha Bora, George Em Karniadakis

Neural operators have emerged as powerful surrogates for modeling complex physical problems. However, they suffer from spectral bias making them oblivious to high-frequency modes, which are present in multiscale physical…

Multi-scale DeepOnet (Mscale-DeepOnet) for Mitigating Spectral Bias in Learning High Frequency Operators of Oscillatory Functions

2025-04-15 · Bo wang, Lizuo Liu, Wei Cai

In this paper, a multi-scale DeepOnet (Mscale-DeepOnet) is proposed to reduce the spectral bias of the DeepOnet in learning high-frequency mapping between highly oscillatory functions, with an application to the nonlinea…