迈向可解释性的一步：涂抹似然
A Step Toward Interpretability: Smearing the Likelihood
AI总结：
本文提出通过涂抹似然定义并识别机器学习所利用的物理能量尺度，证明标度律源于极值理论，并以夸克-胶子喷注识别为例展示区分能力随分辨率降低而提高。
摘要：
粒子物理中机器学习架构的可解释性问题既没有公认的定义，更没有任何被提出的解决方案。我们通过提出一个定义以及相应的实用方法，朝着这些目标迈出了第一个适度的步骤，该方法用于隔离和识别机器所利用的相关物理能量尺度。这是通过涂抹或平均所有在彼此规定度量能量距离内的输入事件来实现的，并相应地使在有限、离散数据集上测量的任何量在数据空间上变得连续。在这种方法中，我们能够明确证明（近似的）标度律是将极值理论应用于分析不可约最小距离分布的结果，机器在给定有限数据集的情况下必须在该距离上进行外推。作为一个例子，我们研究了夸克与胶子喷注识别，构造了涂抹似然，并表明随着分辨率的降低，区分能力稳步提高，这表明该问题的真实似然对所有尺度上的发射都敏感。
英文摘要：
The problem of interpretability of machine learning architecture in particle physics has no agreed-upon definition, much less any proposed solution. We present a first modest step toward these goals by proposing a definition and corresponding practical method for isolation and identification of relevant physical energy scales exploited by the machine. This is accomplished by smearing or averaging over all input events that lie within a prescribed metric energy distance of one another and correspondingly renders any quantity measured on a finite, discrete dataset continuous over the dataspace. Within this approach, we are able to explicitly demonstrate that (approximate) scaling laws are a consequence of extreme value theory applied to analysis of the distribution of the irreducible minimal distance over which a machine must extrapolate given a finite dataset. As an example, we study quark versus gluon jet identification, construct the smeared likelihood, and show that discrimination power steadily increases as resolution decreases, indicating that the true likelihood for the problem is sensitive to emissions at all scales.
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。
