标题： 机器学习模型参数的有效推断 显示英文标题

标题： Valid Inference for Machine Learning Model Parameters

摘要： 机器学习模型的参数通常是通过在一组训练数据上最小化损失函数来学习的。 然而，这可能会带来过拟合的风险；为了使模型能够良好泛化，我们能够找到整个总体上的最优参数非常重要——而不仅仅是给定的训练样本上的最优参数。 在本文中，我们构建了这种机器学习模型最优参数的有效置信集，这些置信集仅使用训练数据即可生成，而无需了解总体。 然后我们表明，研究这个置信集的分布可以使我们为参数空间中的任意区域赋予一种置信度，并且我们证明了可以使用自助法技术很好地近似这种分布。 显示英文摘要

摘要： The parameters of a machine learning model are typically learned by minimizing a loss function on a set of training data. However, this can come with the risk of overtraining; in order for the model to generalize well, it is of great importance that we are able to find the optimal parameter for the model on the entire population -- not only on the given training sample. In this paper, we construct valid confidence sets for this optimal parameter of a machine learning model, which can be generated using only the training data without any knowledge of the population. We then show that studying the distribution of this confidence set allows us to assign a notion of confidence to arbitrary regions of the parameter space, and we demonstrate that this distribution can be well-approximated using bootstrapping techniques.