通过多阶段残差学习缓解量子模型中的频率学习偏差
Mitigating Frequency Learning Bias in Quantum Models via Multi-Stage Residual Learning
AI总结:
本文通过多阶段残差学习方法,缓解量子模型在学习多频率成分时的偏差问题,提升了模型的频谱表达能力。
摘要:
基于参数化电路的量子机器学习模型可以被视为傅里叶级数近似器。然而,它们在学习具有多个频率成分的功能时往往表现不佳,特别是高频率或非主导频率;我们称之为量子傅里叶参数化偏差。受最近在经典傅里叶神经算子(FNOs)中的进展启发,我们将多阶段残差学习思想应用于量子领域,通过迭代训练额外的量子模块来处理前一阶段的残差。我们在一个合成基准上评估了我们的方法,该基准由具有不同包络形状(高斯、洛伦兹、三角形)的空间局部化频率成分组成。系统实验表明,量子比特数量、编码方案和残差学习都是解决多个频率的关键因素;仅残差学习可以在相同总训练轮次下显著提高测试均方误差。我们的工作为增强量子模型的频谱表达能力提供了实用框架,并提供了关于其频率学习行为的新见解。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。