arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.09303cs.LGcs.NAmath.NA
收藏

通过保结构训练稳定物理信息一致性模型

Stabilizing Physics-Informed Consistency Models via Structure-Preserving Training

Institute of Artificial Intelligence Innovation(人工智能创新研究所);National Yang Ming Chiao Tung University(国立阳明交通大学);Department of Applied Mathematics(应用数学系);National Center for Theoretical Sciences(理论科学研究中心);National Taiwan University(国立台湾大学)

Che-Chia Chang, Chen-Yang Dai, Te-Sheng Lin, Ming-Chih Lai, Chieh-Hsin Lai

AI总结:

提出物理信息一致性建模框架,通过保结构两阶段训练策略和两步残差目标,解决物理约束下一致性训练的不稳定性,实现快速、高保真的PDE求解。

摘要:

我们提出了一个物理信息一致性建模框架,通过快速、少步生成推理求解偏微分方程(PDE)。我们识别了物理约束一致性训练中的一个关键稳定性挑战,其中PDE残差可能将模型推向平凡或退化解,从而降低学习到的数据分布。为了解决这个问题,我们引入了一种保结构的两阶段训练策略,通过在物理信息微调期间冻结系数解码器,将分布学习与物理强制执行解耦。我们进一步提出了一个两步残差目标,该目标在精细化的、结构有效的生成轨迹上强制执行物理一致性,而不是在噪声单步预测上。由此产生的框架能够为无条件生成和正问题实现稳定、高保真的推理。我们证明,可以通过基于投影的零样本修复过程获得正问题的解,在计算成本降低数个数量级的同时,达到与扩散基线一致的精度。

英文摘要:

We propose a physics-informed consistency modeling framework for solving partial differential equations (PDEs) via fast, few-step generative inference. We identify a key stability challenge in physics-constrained consistency training, where PDE residuals can drive the model toward trivial or degenerate solutions, degrading the learned data distribution. To address this, we introduce a structure-preserving two-stage training strategy that decouples distribution learning from physics enforcement by freezing the coefficient decoder during physics-informed fine-tuning. We further propose a two-step residual objective that enforces physical consistency on refined, structurally valid generative trajectories rather than noisy single-step predictions. The resulting framework enables stable, high-fidelity inference for both unconditional generation and forward problems. We demonstrate that forward solutions can be obtained via a projection-based zero-shot inpainting procedure, achieving consistent accuracy of diffusion baselines with orders of magnitude reduction in computational cost.

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。

↑