跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2609.11935 · v2

Physics-Informed Conformal Prediction: Embedding PDE Consistency into Distribution-Free Uncertainty Quantification for Neural Operators

首次提交 2026-06-26 11:39
版本更新 2026-11-16 09:43
雷达观测 2026-11-17 17:12
arXiv ↗PDF ↗

摘要

Neural operators such as the Fourier Neural Operator (FNO) achieve high accuracy in approximating solutions to partial differential equations (PDEs), but two fundamental challenges hinder deployment in safety-critical engineering: (1) a structural approximation barrier from FNO's translation equivariance that prevents learning Dirichlet boundary conditions, and (2) the lack of uncertainty bounds when multiple operators are chained in multi-physics cascades. First, we prove that FNO's translation equivariance creates a fundamental approximation barrier for PDEs with non-trivial boundary conditions (Theorem 1), and that coordinate channels resolve this (Theorem 2), validated by up to 63x error reduction across five scenarios. Second, we formalize error propagation in operator cascades: under an explicit TV-Lipschitz condition on downstream conditional mechanisms, we bound the per-stage coverage gap by the stage failure probability plus a mechanism-response term proportional to upstream prediction error (Theorem 3), and show that passing predicted fields between stages degrades coverage far more than error-matched perturbations. On a 3D electromagnetic-thermal-structural cascade, coordinate channels reduce coupling error from 18.5% to 5.0%. For per-stage UQ, we propose Physics-Informed Conformal Prediction (PI-CP), which embeds PDE residuals into the nonconformity score, complementary to recent physics-residual CP (Gopakumar et al., 2025), achieving 89-91% coverage across six physics scenarios. We further identify a boundary of diffusion-based UQ: on well-conditioned forward PDEs, the trained FNO's residual is too small for diffusion models to capture meaningful uncertainty (38-53% coverage). An industrial application, fiber-optic gyroscope bias instability prediction, validates the framework with 3.7-8.0x improvement over analytical baselines.

作者备注:17 pages, 11 tables, 5 figures. v2: Theorem 3 restated under an explicit TV-Lipschitz mechanism condition (v1 formulation invalid); cascade coverage experiments rerun with genuine predicted-field passing plus a no-coupling control

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v2,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v2 · 2026-11-16 09:43 · 最新观测版本

Physics-Informed Conformal Prediction: Embedding PDE Consistency into Distribution-Free Uncertainty Quantification for Neural Operators

Neural operators such as the Fourier Neural Operator (FNO) achieve high accuracy in approximating solutions to partial differential equations (PDEs), but two fundamental challenges hinder deployment in safety-critical engineering: (1) a structural approximation barrier from FNO's translation equivariance that prevents learning Dirichlet boundary conditions, and (2) the lack of uncertainty bounds when multiple operators are chained in multi-physics cascades. First, we prove that FNO's translation equivariance creates a fundamental approximation barrier for PDEs with non-trivial boundary conditions (Theorem 1), and that coordinate channels resolve this (Theorem 2), validated by up to 63x error reduction across five scenarios. Second, we formalize error propagation in operator cascades: under an explicit TV-Lipschitz condition on downstream conditional mechanisms, we bound the per-stage coverage gap by the stage failure probability plus a mechanism-response term proportional to upstream prediction error (Theorem 3), and show that passing predicted fields between stages degrades coverage far more than error-matched perturbations. On a 3D electromagnetic-thermal-structural cascade, coordinate channels reduce coupling error from 18.5% to 5.0%. For per-stage UQ, we propose Physics-Informed Conformal Prediction (PI-CP), which embeds PDE residuals into the nonconformity score, complementary to recent physics-residual CP (Gopakumar et al., 2025), achieving 89-91% coverage across six physics scenarios. We further identify a boundary of diffusion-based UQ: on well-conditioned forward PDEs, the trained FNO's residual is too small for diffusion models to capture meaningful uncertainty (38-53% coverage). An industrial application, fiber-optic gyroscope bias instability prediction, validates the framework with 3.7-8.0x improvement over analytical baselines.

查看此版本解读 →查看此版本原文 ↗