用分块PCA加速椭圆型PDE求解，效率提升3.7倍以上
Localized PCA-Net Neural Operators for Scalable Solution Reconstruction of Elliptic PDEs
- 将解场分块处理，局部做PCA降维再训练神经算子
- 相比全局PCA，端到端速度提升3.7至4倍，精度仍高
- 适合大规模PDE系统中需要快速重建解的场景
神经算子学习已成为数据驱动求解偏微分方程（PDE）的强大方法。然而，对高维解场进行主成分分析（PCA）会带来显著计算开销。为此，我们提出一种基于分块的PCA-Net框架：将解场分解为小块，在每块内执行PCA，再在降维后的PCA空间中训练神经算子。我们研究了两种分块策略——局部到全局和局部到局部，权衡计算效率与重建精度。此外，针对最高效的策略，进一步探索两种改进：(i) 引入重叠块与平滑滤波器，(ii) 采用两步法结合卷积神经网络（CNN）进行精修。结果表明，分块PCA显著降低计算复杂度，保持高精度，使端到端处理时间相较全局PCA减少3.7至4倍，因而成为PDE系统中高效算子学习的有力候选方案。
原文摘要 · Abstract (English)
Neural operator learning has emerged as a powerful approach for solving partial differential equations (PDEs) in a data-driven manner. However, applying principal component analysis (PCA) to high-dimensional solution fields incurs significant computational overhead. To address this, we propose a patch-based PCA-Net framework that decomposes the solution fields into smaller patches, applies PCA within each patch, and trains a neural operator in the reduced PCA space. We investigate two different patch-based approaches that balance computational efficiency and reconstruction accuracy: (1) local-to-global patch PCA, and (2) local-to-local patch PCA. The trade-off between computational cost and accuracy is analyzed, highlighting the advantages and limitations of each approach. Furthermore, within each approach, we explore two refinements for the most computationally efficient method: (i) introducing overlapping patches with a smoothing filter and (ii) employing a two-step process with a convolutional neural network (CNN) for refinement. Our results demonstrate that patch-based PCA significantly reduces computational complexity while maintaining high accuracy, reducing end-to-end pipeline processing time by a factor of 3.7 to 4 times compared to global PCA, thefore making it a promising technique for efficient operator learning in PDE-based systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。