arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.03642cs.LG
收藏

Transformer驱动的代理模型以极有限数据弥合ICF模拟与实验差距

Transformer-Powered Surrogates Close the ICF Simulation-Experiment Gap with Extremely Limited Data

Lawrence Livermore National Laboratory(劳伦斯利弗莫尔国家实验室);Oregon State University(俄勒冈州立大学)

Matthew L. Olson, Shusen Liu, Jayaraman J. Thiagarajan, Bogdan Kustowski, Weng-Keen Wong, Rushil Anirudh

AI总结:

本文提出一种结合Transformer架构与图基超参数优化的代理模型,在仅有10次真实数据的ICF实验中有效降低模拟偏差并提升预测精度。

摘要:

机器学习的最新进展,特别是Transformer架构,已在商业领域取得了显著突破。这些强大的模型展现出学习复杂关系的卓越能力,并且通常能更好地泛化到新数据和问题。本文提出了一种新颖的基于Transformer的方法,用于提升多模态输出场景中的预测精度,其中稀疏的实验数据由模拟数据补充。所提出的方法将基于Transformer的架构与一种新颖的基于图的超参数优化技术相结合。由此产生的系统不仅有效降低了模拟偏差,而且与先前方法相比实现了更优的预测精度。我们在惯性约束聚变实验中验证了该方法的有效性,这些实验仅有10次真实世界数据可用,同时也在这些实验的合成版本上进行了验证。

英文摘要:

Recent advances in machine learning, specifically transformer architecture, have led to significant advancements in commercial domains. These powerful models have demonstrated superior capability to learn complex relationships and often generalize better to new data and problems. This paper presents a novel transformer-powered approach for enhancing prediction accuracy in multi-modal output scenarios, where sparse experimental data is supplemented with simulation data. The proposed approach integrates transformer-based architecture with a novel graph-based hyper-parameter optimization technique. The resulting system not only effectively reduces simulation bias, but also achieves superior prediction accuracy compared to the prior method. We demonstrate the efficacy of our approach on inertial confinement fusion experiments, where only 10 shots of real-world data are available, as well as synthetic versions of these experiments.

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。

↑