Conformal prediction is a widely-used framework for distribution-free uncertainty quantification, which generates valid prediction sets at a user-defined significance level. However, this framework relies on the assumption that the data-generating distribution is exchangeable, a condition that is frequently violated in time-series and other structured data. In such cases, the validity guarantees of conformal prediction break down. Adaptive conformal inference (ACI) has been proposed as a solution for non-exchangeable data by dynamically adjusting the significance level to retain at least finite sample guarantees on the marginal coverage error rate. This paper demonstrates that, despite its name, ACI does not strictly require the use of conformal predictors. Instead, it can operate effectively with the more general concept of a confidence predictor, which is often computationally simpler. The key requirement is that larger significance levels correspond to smaller prediction sets, a property known as nested prediction sets. Through experiments on synthetic and real-world data, we investigate whether ACI with conformal predictors offers advantages over confidence predictors. Our results indicate that confidence predictors can perform just as well, and sometimes better than conformal predictors in some cases, although further empirical studies are needed to determine when one approach may be preferable.

该研究解决了保形预测在时间序列和结构化数据中的有效性问题，提出自适应保形推断（ACI）作为一种动态调整显著性水平的方法。研究表明，尽管ACI强调保形预测，但实际上更灵活地适用于信心预测，并发现信心预测在某些情况下表现不逊色于保形预测。 

自适应保形推断并非保形