发表机构
University of Pennsylvania（宾夕法尼亚大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出利用能量移动距离对事件进行相似性配对，替代数据增强，在LHC上通过自蒸馏预训练QCD喷注，获得语义嵌入，下游性能优于或媲美增强基线。
AI 中文摘要
在大型强子对撞机（LHC）上训练基础模型的许多自监督方法依赖于数据增强，以鼓励模型将事件嵌入到对某些物理或探测器对称性不变的表征空间中。一个常见的挑战来自于选择合适增强集的巨大自由度，下游性能依赖于这些增强。增强的实现涉及要么修改现有事件，可能破坏事件保真度，要么模拟更多事件变体，这计算强度大。在这项工作中，我们提出了一种数据驱动的方法，通过能量移动距离（EMD）对事件进行相似性配对，该距离衡量两个事件在将一个转换为另一个所需功方面的相似程度。通过这种方法，不同的事件被采样并根据其相似性进行匹配，作为学习不变性的视图，同时保持每个事件的物理内容完整，无需手工设计的扭曲。我们通过自蒸馏在QCD喷注上预训练来演示这种无增强的配对方法，并表明它可以产生语义喷注嵌入，其下游判别能力与基于增强的基线相当或更好。
英文摘要
Many self-supervised methods for training foundation models at the Large Hadron Collider (LHC) rely on data augmentations to encourage the model to embed events into a representation space invariant to certain physical or detector symmetries. A common challenge arises from the large freedom in choosing a proper set of augmentations on which downstream performance depends. The implementation of augmentations involves either modifying existing events, potentially breaking the event fidelity, or simulating more event variants, which is computationally intensive. In this work, we present a data-driven method of pairing events by their similarity via the energy mover's distance (EMD), which measures how similar two events are in terms of the work required to transform one into the other. With this approach, distinct events are sampled and matched by their similarity to serve as views for learning invariance, keeping the physics content of each event intact without handcrafted distortions. We demonstrate this augmentation-free pairing method by pre-training on QCD jets via self-distillation and show that it can yield semantic jet embeddings with downstream discrimination power comparable to or better than an augmentation-based baseline.
Comments6 pages
