INEUS neural solver tackles high-dimensional PIDEs with iterative regression

Researchers have developed INEUS, a novel meshfree iterative neural solver designed to tackle high-dimensional partial integro-differential equations (PIDEs). This method enhances efficiency by employing single-jump sampling for nonlocal integrals and framing PIDE solutions as recursive regression problems. INEUS offers a more computationally tractable approach to nonlocal terms compared to traditional Physics-Informed Neural Networks (PINNs), demonstrating accurate and scalable results across various high-dimensional linear and nonlinear PIDE examples. AI

影响 Introduces a new neural network approach for solving high-dimensional PIDEs, potentially advancing scientific computing and simulation capabilities.

排序理由 This is a research paper introducing a new method for solving complex mathematical equations using neural networks. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

• arXiv
• INEUS

• 论文
• 其他

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →