Adversarially-trained autoencoders for robust unsupervised new physics searches
Adversarially-trained autoencoders for robust unsupervised new physics searches
复制标题
DOI：
10.1007/jhep10(2019)047
复制
发表时间：
2019-10-04
影响因子：
5.4
通讯作者：
Waite, Philip
中科院分区：
文献类型：
--
作者：
Blance, Andrew;Spannowsky, Michael;Waite, Philip
粒子物理学中的机器学习技术在直接根据数据进行训练时最为强大，以避免对理论不确定性或预期信号的潜在偏差敏感。为了能够在搜索新物理学的数据上进行训练，异常检测方法是必不可少的，这可以通过自动编码器作为无监督分类器来实现。影响分类器的最后一个不确定性来源是最终状态对象重建中的实验不确定性。为了减轻它们对分类器的影响，并允许对该方法进行现实的评估，我们建议将自动编码器与对抗性神经网络联合收割机相结合，以消除其对最终状态对象的涂抹的敏感性。我们量化其效果，并表明，可以实现一个强大的异常检测共振诱导的t（t）杆的最终状态。
Machine learning techniques in particle physics are most powerful when they are trained directly on data, to avoid sensitivity to theoretical uncertainties or an underlying bias on the expected signal. To be able to train on data in searches for new physics, anomaly detection methods are imperative, which can be realised by an autoencoder acting as an unsupervised classifier. The last source of uncertainties affecting the classifier are then experimental uncertainties in the reconstruction of the final-state objects. To mitigate their effect on the classifier and to allow for a realistic assessment of the method, we propose to combine the autoencoder with an adversarial neural network to remove its sensitivity to the smearing of the final-state objects. We quantify its effect and show that one can achieve a robust anomaly detection in resonance-induced t (t) over bar final states.