用局部敏感哈希优化Mamba模型，提升高能物理长序列处理速度与精度。
Application of Structured State Space Models to High energy physics with locality-sensitive hashing
- 将局部敏感哈希嵌入Mamba块，增强局部特征捕捉能力。
- 在关键任务中推理速度更快，FLOPS降低，物理指标更优。
- 适合需要高效处理海量点云与长序列的高能物理研究者。
现代高能物理实验面临数据规模与复杂性日益增长的挑战，尤其体现在大规模点云处理和长序列分析上。本文探索结构化状态空间模型（SSMs）在该领域的应用，首次将局部敏感哈希（LSH）引入纯或混合Mamba模型中。结果表明，纯SSMs可作为具备局部归纳偏置的长序列任务强大骨干网络。通过在Mamba模块中集成局部敏感哈希，本方法在关键高能物理任务中显著优于传统骨干网络，在推理速度、物理指标方面表现更佳，同时降低计算开销。在核心测试中，该方法显著减少浮点运算量（FLOPS），同时保持优异性能，为替代传统Transformer骨干提供可行方案。
原文摘要 · Abstract (English)
Modern high-energy physics (HEP) experiments are increasingly challenged by the vast size and complexity of their datasets, particularly regarding large-scale point cloud processing and long sequences. In this study, to address these challenges, we explore the application of structured state space models (SSMs), proposing one of the first trials to integrate local-sensitive hashing into either a hybrid or pure Mamba Model. Our results demonstrate that pure SSMs could serve as powerful backbones for HEP problems involving tasks for long sequence data with local inductive bias. By integrating locality-sensitive hashing into Mamba blocks, we achieve significant improvements over traditional backbones in key HEP tasks, surpassing them in inference speed and physics metrics while reducing computational overhead. In key tests, our approach demonstrated promising results, presenting a viable alternative to traditional transformer backbones by significantly reducing FLOPS while maintaining robust performance.
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。