发表机构
MIT Lincoln Laboratory（麻省理工学院林肯实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出基于Rényi--Chernoff信息的路径证书，用于认证去中心化自适应感知系统，证明信息线性增长可实现指数误差衰减，并揭示最差竞争者作为性能瓶颈。研究结果提供了一种利用实际收集证据来认证和诊断自适应多智能体感知系统的实用方法。
AI 中文摘要
我们研究去中心化自适应感知问题，其中多个智能体根据不断演化的局部信念选择测量，并通过通信图交换信息。我们询问自适应策略实际选择的测量是否已收集到足够的证据，以将真实目标与每个合理的备选目标区分开来。我们基于沿实际感知轨迹累积的Rényi--Chernoff信息，开发了一种路径证书。该证书为非渐近MAP误差界以及任意依赖于历史的感知策略提供了随时可用的、网络范围的停止规则，同时将累积的统计信息与有界的网络混合瞬态分离开来。信息相对于最不具分辨力的竞争者的线性增长意味着MAP误差和平方定位误差的指数衰减。一个经典的成对KL逆定理，专门适用于自适应去中心化转录，表明任何一对上的信息不足都会阻止正的均匀误差指数，从而确认最难的竞争者是一个基本瓶颈。在不同策略、图拓扑、传感器配置和种子下，最差竞争者的得分与定位速度的相关性比平均对代理更强，在1D（$r=0.89$对比$0.40$）和结构化2D感知（$r=0.77$对比$0.48$）中均如此。我们的结果为认证和诊断自适应多智能体感知系统提供了一种实用方法，利用它们实际收集的证据。
英文摘要
We study decentralized adaptive sensing, where multiple agents choose measurements from evolving local beliefs while exchanging information over a communication graph. We ask whether the measurements actually selected by an adaptive policy have collected enough evidence to distinguish the true target from every plausible alternative. We develop a pathwise certificate based on the Rényi--Chernoff information accumulated along the realized sensing trajectory. It yields nonasymptotic MAP-error bounds and an anytime, network-wide stopping rule for arbitrary history-dependent sensing policies, while separating accumulated statistical information from a bounded network-mixing transient. Linear growth of the information against the least-resolved competitor implies exponential decay of MAP and squared-localization error. A classical pairwise KL converse, specialized to the adaptive decentralized transcript, shows that insufficient information on any pair prevents a positive uniform error exponent, confirming the hardest competitor as a fundamental bottleneck. Across policies, graph topologies, sensor profiles, and seeds, the worst-competitor score correlates more strongly with localization speed than an average-pair proxy in both 1D ($r=0.89$ versus $0.40$) and structured 2D sensing ($r=0.77$ versus $0.48$). Our results provide a practical way to certify and diagnose adaptive multi-agent sensing systems using the evidence they actually collect.
Comments26 pages, preprint
