BitHEP -- 低精度机器学习在粒子物理学中的局限性
BitHEP -- The Limits of Low-Precision ML in HEP
AI总结:
BitHEP研究了BitNet在高能物理中的应用,发现其在分类任务中表现良好,但在回归和生成任务中存在性能差异,揭示了其局限性。
摘要:
现代神经网络架构的日益复杂性要求快速且内存高效的实现以缓解计算瓶颈。在本工作中,我们评估了最近提出的BitNet架构在粒子物理应用中的表现,评估其在分类、回归和生成建模任务中的性能。具体而言,我们研究其在夸克-胶子鉴别、SMEFT参数估计和探测器模拟中的适用性,并将其效率和准确性与最先进的方法进行比较。我们的结果表明,虽然BitNet在分类任务中表现一贯具有竞争力,但其在回归和生成任务中的表现会随着网络大小和类型而变化,突显了关键的局限性和潜在的改进领域。
英文摘要:
The increasing complexity of modern neural network architectures demands fast and memory-efficient implementations to mitigate computational bottlenecks. In this work, we evaluate the recently proposed BitNet architecture in HEP applications, assessing its performance in classification, regression, and generative modeling tasks. Specifically, we investigate its suitability for quark-gluon discrimination, SMEFT parameter estimation, and detector simulation, comparing its efficiency and accuracy to state-of-the-art methods. Our results show that while BitNet consistently performs competitively in classification tasks, its performance in regression and generation varies with the size and type of the network, highlighting key limitations and potential areas for improvement.
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。