In this paper, we analyze the impact of data freshness on remote inference systems, where a pre-trained neural network infers a time-varying target (e.g., the locations of vehicles and pedestrians) based on features (e.g., video frames) observed at a sensing node (e.g., a camera). One might expect that the performance of a remote inference system degrades monotonically as the feature becomes stale. Using an information-theoretic analysis, we show that this is true if the feature and target data sequence can be closely approximated as a Markov chain, whereas it is not true if the data sequence is far from Markovian. Hence, the inference error is a function of Age of Information (AoI), where the function could be non-monotonic. To minimize the inference error in real-time, we propose a new "selection-from-buffer" model for sending the features, which is more general than the "generate-at-will" model used in earlier studies. In addition, we design low-complexity scheduling policies to improve inference performance. For single-source, single-channel systems, we provide an optimal scheduling policy. In multi-source, multi-channel systems, the scheduling problem becomes a multi-action restless multi-armed bandit problem. For this setting, we design a new scheduling policy by integrating Whittle index-based source selection and duality-based feature selection-from-buffer algorithms. This new scheduling policy is proven to be asymptotically optimal. These scheduling results hold for minimizing general AoI functions (monotonic or non-monotonic). Data-driven evaluations demonstrate the significant advantages of our proposed scheduling policies.

翻译：本文分析了数据新鲜度对远程推理系统的影响，其中预训练神经网络基于传感节点（如摄像头）观测到的特征（如视频帧）来推理时变目标（如车辆和行人的位置）。人们可能预期远程推理系统的性能会随着特征过时而单调下降。通过信息论分析，我们证明：当特征与目标数据序列可近似为马尔可夫链时，该结论成立；而当数据序列远离马尔可夫性质时，该结论不成立。因此，推理误差是信息年龄（AoI）的函数，该函数可能非单调。为实时最小化推理误差，我们提出了一种新的"从缓冲区选择"特征发送模型，该模型比早期研究中使用的"按需生成"模型更具一般性。此外，我们设计了低复杂度调度策略以提升推理性能。针对单源单信道系统，我们给出了最优调度策略。在多源多信道系统中，调度问题转化为多动作无穷臂赌博机问题。针对这一场景，我们通过融合基于Whittle指数的源选择算法和基于对偶性的特征选择缓冲区算法，设计了新的调度策略，并证明该策略具有渐进最优性。上述调度结果适用于最小化一般信息年龄函数（单调或非单调）。基于数据驱动的评估验证了所提调度策略的显著优势。