论文标题
关于精选的现代深度学习技术对实验性高能物理用例中分类模型的性能和分类模型的影响
On the impact of selected modern deep-learning techniques to the performance and celerity of classification models in an experimental high-energy physics use case
论文作者
论文摘要
从基本的神经网络架构开始，我们在使用精心研究的数据集（2014 Higgs Higgs ML Kaggle Data aset）中，在高能物理学的范围内遇到的典型分类问题，通过一系列高级技术（尤其是深度学习）来测试一系列的高级技术，尤其是深度学习。根据性能指标和训练和应用最终模型所需的时间评估优势。所检查的技术包括特定于域的数据启发，学习率和动量调度，（高级）在模型空间和重量空间中结合，以及替代体系结构和连接方法。调查后，我们得出了一个模型，该模型与原始Kaggle挑战的获胜解决方案相同，同时更快地训练和申请，并且适合与GPU和CPU硬件设置一起使用。这些定时和硬件需求的减少可能允许在HEP分析中使用更强大的算法，在这种分析中，必须经常被有限的硬件资源的研究人员频繁地（有时在短时间内）重新训练。此外，还提出了一个名为Lumin的新包装库，其中包含了所有研究的技术。
Beginning from a basic neural-network architecture, we test the potential benefits offered by a range of advanced techniques for machine learning, in particular deep learning, in the context of a typical classification problem encountered in the domain of high-energy physics, using a well-studied dataset: the 2014 Higgs ML Kaggle dataset. The advantages are evaluated in terms of both performance metrics and the time required to train and apply the resulting models. Techniques examined include domain-specific data-augmentation, learning rate and momentum scheduling, (advanced) ensembling in both model-space and weight-space, and alternative architectures and connection methods. Following the investigation, we arrive at a model which achieves equal performance to the winning solution of the original Kaggle challenge, whilst being significantly quicker to train and apply, and being suitable for use with both GPU and CPU hardware setups. These reductions in timing and hardware requirements potentially allow the use of more powerful algorithms in HEP analyses, where models must be retrained frequently, sometimes at short notice, by small groups of researchers with limited hardware resources. Additionally, a new wrapper library for PyTorch called LUMIN is presented, which incorporates all of the techniques studied.
