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 2606.18403hep-ph
收藏

使用机器学习对快速重建流水线进行压力测试

Stress testing of fast reconstruction pipelines using machine learning

Central University of South Bihar(南比哈尔中央大学)

Swagata Ghosh

AI总结:

针对快速重建流水线中局部假设的鲁棒性问题,提出一种领域无关的上下文感知压力测试方法,并在HL-LHC模拟中揭示Z→ℓℓ通道的局部假设失效导致重建偏差和分辨率下降,通过无监督域映射框架恢复峰值稳定性。

摘要:

快速重建和探测器模拟流水线广泛应用于不同科学领域,例如高能物理(HEP)和医学成像,其中完整的实验或设备级模拟在计算上具有挑战性。这些流水线不使用全局数据上下文,而是采用简化的响应模型,假设重建不确定性依赖于局部输入参数。为了检验局部假设的鲁棒性,引入了一种领域无关的上下文感知压力测试流水线,并允许依赖于全局参数的重建响应。以高亮度LHC(HL-LHC)模拟中的HEP实例为例,本工作表明,衰变通道$Z \rightarrow \ell\ell$作为基准,违反了局部假设,导致显著的重建偏差和分辨率下降。利用无监督域映射框架,本工作还恢复了这种峰值稳定性并恢复了真实水平的分辨率,为下一代快速模拟流水线提供了一种鲁棒的诊断工具。

英文摘要:

The fast reconstruction and detector-simulation pipelines are widely used in different scientific domains, such as, in High Energy Physics (HEP) and medical imaging, where the full experimental or the device-level simulation is computationally challenging. Instead of the use of the global data context, these pipelines use simplified response models which assume reconstruction uncertainty relies on local input parameters. To probe the robustness of the local assumption, a domain-agnostic context-aware stress testing pipeline is introduced, and a reconstruction response depending on the global parameters is also allowed. For an instance in HEP at High-Luminosity LHC (HL-LHC) simulation, this work shows that the decay channel $Z \rightarrow \ell\ell$, as a benchmark, violates the local assumption resulting in a significant reconstruction bias and resolution degradation. Using the unsupervised regime-mapping framework, this work also restores this peak stability and recovers the truth-level resolution, where a robust diagnostic tool for next-generation fast simulation pipelines is accommodated.

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。

↑