LTAU-FF:原子力场中基于损失轨迹分析的不确定性量化
LTAU-FF: Loss Trajectory Analysis for Uncertainty in Atomistic Force Fields
AI总结:
本文提出LTAU方法,利用训练误差分布和潜在空间相似性搜索,快速估计原子力场预测不确定性,速度比集成快2-3个数量级,并展示其在域外检测、性能调优和故障预测中的应用。
摘要:
模型集成是估计深度学习原子力场预测不确定性的有效工具。然而,其广泛应用受到高计算成本和过度自信的误差估计的阻碍。在本工作中,我们通过利用训练过程中获得的每个样本误差的分布,并在模型潜在空间中进行基于距离的相似性搜索来解决这些挑战。我们提出的方法称为LTAU,利用记录的训练误差高效地估计任何测试点的完整误差概率分布函数(PDF),其速度比典型的集成方法快2-3个数量级,从而使其能够用于训练或评估多个模型不可行的任务。我们将LTAU应用于估计原子力场中的参数不确定性(LTAU-FF),证明其改进的集成多样性能够产生校准良好的置信区间,并且对于训练域附近的数据,预测的误差与真实误差强相关。此外,我们展示了LTAU-FF预测的误差可用于实际应用,如检测域外数据、调整模型性能以及预测模拟过程中的失败。我们相信LTAU将成为原子力场中不确定性量化(UQ)的宝贵工具,并且是一种有前景的方法,值得在机器学习其他领域进一步探索。
英文摘要:
Model ensembles are effective tools for estimating prediction uncertainty in deep learning atomistic force fields. However, their widespread adoption is hindered by high computational costs and overconfident error estimates. In this work, we address these challenges by leveraging distributions of per-sample errors obtained during training and employing a distance-based similarity search in the model latent space. Our method, which we call LTAU, efficiently estimates the full probability distribution function (PDF) of errors for any test point using the logged training errors, achieving speeds that are 2--3 orders of magnitudes faster than typical ensemble methods and allowing it to be used for tasks where training or evaluating multiple models would be infeasible. We apply LTAU towards estimating parametric uncertainty in atomistic force fields (LTAU-FF), demonstrating that its improved ensemble diversity produces well-calibrated confidence intervals and predicts errors that correlate strongly with the true errors for data near the training domain. Furthermore, we show that the errors predicted by LTAU-FF can be used in practical applications for detecting out-of-domain data, tuning model performance, and predicting failure during simulations. We believe that LTAU will be a valuable tool for uncertainty quantification (UQ) in atomistic force fields and is a promising method that should be further explored in other domains of machine learning.
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。