发表机构
Sandia National Laboratories; University of Southern California; Brown University; Oak Ridge National Laboratory（桑迪亚国家实验室; 南加州大学; 布朗大学; 橡树岭国家实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对潜在神经代理求解器长时程展开误差累积问题，本文提出训练层面干预措施，将潜在表示与长时程展开对齐，将长展开误差降低约40%，并达到或超过全分辨率模型精度，同时大幅降低计算成本。
AI 中文摘要
潜在神经代理求解器，即潜在动力学模型，通过演化压缩的潜在空间而非直接解析全分辨率场，加速了含时物理系统的模拟。原则上，这降低了计算成本并简化了学习，但在实践中，误差在长自回归展开过程中往往迅速累积，限制了预测的实用性。我们表明，这种不稳定性并非源于潜在表示本身，而是当其仅针对重建进行训练时产生的，导致表示不适合长时程预测。我们系统地评估了训练层面的干预措施，使潜在表示与长时程展开对齐：在自编码器训练期间进行Koopman算子学习和Hamming噪声注入以改善压缩，同时结合噪声注入和多步展开微调以改善动力学。改善长时程展开稳定性的干预措施通常会降低传统训练指标，包括重建和单步预测精度。总体而言，这些干预措施将长展开误差降低约40%，并在两个物理基准上达到或超过全分辨率模型的精度，同时所需的浮点运算次数少2个数量级，GPU内存减半。应用于高周疲劳的介观晶体塑性模拟时，所得代理在远超训练期间观察到的时程上实现了稳定的外推。更广泛地说，这些结果表明，神经压缩的设计不应仅仅为了降低维度，而应重构解空间以实现稳定的动力学演化，这是科学应用中可靠、高效神经代理的关键要求。
英文摘要
Latent neural surrogate solvers, or latent dynamics models, accelerate simulations of time-dependent physical systems by evolving a compressed latent space rather than resolving full-resolution fields directly. In principle this reduces computational cost and simplifies learning, but in practice errors often accumulate rapidly during long autoregressive rollouts, limiting predictive utility. We show that this instability does not stem from the latent representation itself, but arises when it is trained solely for reconstruction, producing representations poorly suited to long-horizon forecasting. We systematically evaluate training-level interventions that align latent representations with long-horizon rollout: Koopman operator learning and Hamming noise injection during autoencoder training to improve compression, together with noise injection and multi-step rollout fine-tuning to improve dynamics. Interventions that improve long-horizon rollout stability often degrade conventional training metrics, including reconstruction and one-step prediction accuracy. Collectively, these interventions reduce long-rollout error by approximately 40\% and match or exceed the accuracy of full-resolution models on two physics benchmarks, while requiring 2 orders of magnitude fewer floating point operations and half the GPU memory. Applied to mesoscale crystal-plasticity simulations of high-cycle fatigue, the resulting surrogate achieves stable extrapolation over horizons orders of magnitude beyond those observed during training. More broadly, these results show that neural compression should be designed not merely to reduce dimensionality, but to restructure the solution space for stable dynamical evolution, a key requirement for reliable, efficient neural surrogates in scientific applications.
