Early-exit neural networks (EENNs) facilitate adaptive inference by producing predictions at multiple stages of the forward pass. In safety-critical applications, these predictions are only meaningful when complemented with reliable uncertainty estimates. Yet, due to their sequential structure, an EENN's uncertainty estimates should also be consistent: labels that are deemed improbable at one exit should not reappear within the confidence interval / set of later exits. We show that standard uncertainty quantification techniques, like Bayesian methods or conformal prediction, can lead to inconsistency across exits. We address this problem by applying anytime-valid confidence sequences (AVCSs) to the exits of EENNs. By design, AVCSs maintain consistency across exits. We examine the theoretical and practical challenges of applying AVCSs to EENNs and empirically validate our approach on both regression and classification tasks.

翻译：早期退出神经网络（EENNs）通过在前向传播的多个阶段生成预测，支持自适应推理。在安全关键型应用中，这些预测仅在辅以可靠的不确定性估计时才具有实际意义。然而，由于EENNs具有序列化结构，其不确定性估计还需保持一致性：即在一个退出点被认定为低概率的标签，不应再次出现在后续退出点的置信区间/集合中。我们证明，标准的不确定性量化技术（如贝叶斯方法或保形预测）可能导致各退出点之间的不一致性。为此，我们通过将随时有效性置信序列（AVCSs）应用于EENNs的退出点来解决该问题。从设计原理上讲，AVCSs能够维持各退出点之间的一致性。我们深入研究了将AVCSs应用于EENNs的理论与实践挑战，并通过回归与分类任务实证验证了所提方法的有效性。