等变变换器的优点与缺点
Virtues and Vices of Equivariant Transformers
浏览论文内容
中文总结 AI 辅助
研究洛伦兹等变变换器在大尺寸喷注与味道标记中的表现，优化其推理成本后发现，几何特征相关时其性能优于标准变换器，可为LHC数据基础模型开发提供参考。
中文摘要 AI 辅助
我们首次研究洛伦兹等变变换器在大尺寸喷注标记和味道标记中的优势，为控制计算需求，我们针对推理成本指标优化所有实现。在缩放研究中发现，只要几何特征相关，洛伦兹等变网络的性能优于标准变换器，这在理想情况和资源有限时均成立。洛伦兹等变带来的条件增益，为大型强子对撞机（LHC）数据的基础模型开发提供了有趣的参考。
英文摘要
We study for the first time the benefit of Lorentz-equivariant transformers for large-size jet tagging and flavor tagging. To control their computing demands, we optimize all implementations for inference cost metrics. In our scaling studies, we find that Lorentz-equivariant networks outperform standard transformers, provided geometric features are relevant. This holds true in an idealized world as well as for limited resources. The conditional gain from Lorentz equivariance provides interesting input to the development of foundation models for LHC data.
