标题： 粒子物理数据中的双下降和过度参数化 显示英文标题

标题： Double Descent and Overparameterization in Particle Physics Data

摘要： 最近，在机器学习任务中观察到了高度过参数化模型的优势：具有足够容量以轻松跨越\emph{插值阈值}的模型，其泛化误差相比经典偏差-方差权衡范式有所改善。我们首次在粒子物理数据中展示了这种行为，并探讨了“双重下降”出现的时间和地点，以及在何种情况下过参数化会导致性能提升。 显示英文摘要

摘要： Recently, the benefit of heavily overparameterized models has been observed in machine learning tasks: models with enough capacity to easily cross the \emph{interpolation threshold} improve in generalization error compared to the classical bias-variance tradeoff regime. We demonstrate this behavior for the first time in particle physics data and explore when and where `double descent' appears and under which circumstances overparameterization results in a performance gain.