Simulation-based inference methods that feature correct conditional coverage of confidence sets based on observations that have been compressed to a scalar test statistic require accurate modelling of either the p-value function or the cumulative distribution function (cdf) of the test statistic. If the model of the cdf, which is typically a deep neural network, is a function of the test statistic then the derivative of the neural network with respect to the test statistic furnishes an approximation of the sampling distribution of the test statistic. We explore whether this approach to modelling conditional 1-dimensional sampling distributions is a viable alternative to the probability density-ratio method, also known as the likelihood-ratio trick. Relatively simple, yet effective, neural network models are used whose predictive uncertainty is quantified through a variety of methods.

翻译：基于模拟的推断方法通过对观测数据压缩为标量检验统计量，能够实现置信集的条件正确覆盖。这类方法需要对检验统计量的p值函数或累积分布函数（cdf）进行精确建模。若cdf模型（通常采用深度神经网络）以检验统计量为自变量，则神经网络对该统计量的导数可提供其抽样分布的近似表征。本文探究这种对条件一维抽样分布进行建模的方法，是否可作为概率密度比方法（又称似然比技巧）的可行替代方案。我们采用结构相对简单但性能有效的神经网络模型，并通过多种方法对其预测不确定性进行量化。