DisCo Fever：通过距离相关的鲁棒网络
DisCo Fever: Robust Networks Through Distance Correlation
摘要：
虽然深度学习在大型强子对撞机及其他领域的监督分类任务中非常成功，但对于实际应用，原始分类精度往往不是唯一的考虑因素。一个关键问题是网络预测的稳定性，无论是对输入数据的个别特征的变化，或对系统扰动。我们提出了一种新的方法的基础上的一个新的应用程序的“距离相关性”（DisCo），量化非线性相关性的措施，达到同等性能的最先进的对抗性去相关网络，但更简单，更稳定的训练。为了证明我们的方法的有效性，我们仔细地重铸最近的ATLAS研究的去相关方法，适用于增强，强子W-标记。我们还展示了DisCo正则化对于更强大的卷积神经网络以及强子顶部标记问题的可行性。
英文摘要：
While deep learning has proven to be extremely successful at supervised classification tasks at the LHC and beyond, for practical applications, raw classification accuracy is often not the only consideration. One crucial issue is the stability of network predictions, either versus changes of individual features of the input data, or against systematic perturbations. We present a new method based on a novel application of "distance correlation" (DisCo), a measure quantifying non-linear correlations, that achieves equal performance to state-of-the-art adversarial decorrelation networks but is much simpler and more stable to train. To demonstrate the effectiveness of our method, we carefully recast a recent ATLAS study of decorrelation methods as applied to boosted, hadronic W-tagging. We also show the feasibility of DisCo regularization for more powerful convolutional neural networks, as well as for the problem of hadronic top tagging.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
