发现粒子物理幅度代理模型的性能与数据量、算力、规模的缩放规律
Scaling laws for amplitude surrogates
- 基于粒子物理幅度代理，研究神经网络性能随数据、算力、规模的变化规律
- 发现缩放系数与过程外部粒子数直接相关，可预测模型表现
- 为实现特定精度目标提供高效计算策略，适合高能物理研究者
描述神经网络性能随训练数据量、计算资源投入和网络规模变化的缩放规律，在众多机器学习任务和数据集上已广泛出现。本文系统研究了这些缩放规律在粒子物理幅度代理中的应用。结果表明，缩放系数与过程的外部粒子数量密切相关。研究证明，缩放规律是实现预定精度目标的有力工具。
原文摘要 · Abstract (English)
Scaling laws describing the dependence of neural network performance on the amount of training data, the spent compute, and the network size have emerged across a huge variety of machine learning task and datasets. In this work, we systematically investigate these scaling laws in the context of amplitude surrogates for particle physics. We show that the scaling coefficients are connected to the number of external particles of the process. Our results demonstrate that scaling laws are a useful tool to achieve desired precision targets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。