用对比学习缓解物理模拟与真实数据的差异问题。
MACK: Mismodeling Addressed with Contrastive Knowledge
- 基于对比学习设计通用方法，无需事先知道偏差细节。
- 在大型强子对撞机喷注识别任务中显著提升模型鲁棒性。
- 适用于高能物理及其他领域，尤其适合仿真与实测有偏差场景。
机器学习在高能物理中的应用通常依赖大量精确的模拟数据进行训练。随着模型复杂度增加，其对模拟数据与实验实测数据之间的差异愈发敏感。本文提出一种基于对比学习的通用方法，可有效缓解这一负面影响。该方法的关键优势在于无需预先知晓具体偏差特征。我们以大型强子对撞机上的喷注识别任务为例，验证了该技术的有效性，且其适用范围涵盖高能物理内外的多种任务。
原文摘要 · Abstract (English)
The use of machine learning methods in high energy physics typically relies on large volumes of precise simulation for training. As machine learning models become more complex they can become increasingly sensitive to differences between this simulation and the real data collected by experiments. We present a generic methodology based on contrastive learning which is able to greatly mitigate this negative effect. Crucially, the method does not require prior knowledge of the specifics of the mismodeling. While we demonstrate the efficacy of this technique using the task of jet-tagging at the Large Hadron Collider, it is applicable to a wide array of different tasks both in and out of the field of high energy physics.
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。