NAE,统计上
NAE, Statistically
中文总结 AI 辅助
本研究针对神经异常分数新物理搜索的统计可解释性问题,提出归一化自编码器(NAE),经玩具模型、双NAE喷注测试验证其概率解释性,还展示贝叶斯NAE可学习带不确定性的似然。
中文摘要 AI 辅助
利用神经异常分数寻找新物理具有变革性潜力,但缺乏统计可解释性。归一化自编码器(NAE)为标准瓶颈架构提供概率解释,将异常分数与学习到的似然关联。我们在玩具模型上验证该关系,采用双NAE设置对喷注进行测试,并展示贝叶斯NAE如何学习带不确定性的似然。
英文摘要
Searches for new physics using neural anomaly scores have transformative potential, but suffer from a lack of statistical interpretability. The normalized autoencoder (NAE) provides a probabilistic interpretation of the standard bottleneck architecture, tying the anomaly score to a learned likelihood. We validate this relation for a toy model, test it for jets using a dual-NAE setup, and show how a Bayesian NAE learns this likelihood with an uncertainty.