发表机构
University of Glasgow（格拉斯哥大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对间歇连接去中心化学习中的同伴选择，提出基于易逝证据的最优停止理论PROSE，证明保留值策略并给出移动感知停止规则，实现轻量级本地决策。
AI 中文摘要
去中心化联邦学习移除了聚合服务器，但使协作依赖于瞬时的同伴可用性。在移动和间歇连接系统中，评估一个有前景的同伴会消耗接触时间，并可能导致交换机会本身消失，因此学习者收集到的关于同伴的证据是易逝的：它会因链路过期以及旧测量值老化时同伴模型漂移而衰减。本文针对由此产生的同伴选择问题，发展了一套自洽的最优停止理论。我们将接收者在接触内的决策形式化为一个有限时域马尔可夫最优停止问题，该问题具有昂贵的信息获取和未来到达的外部选项，并证明其存在一个由保留值（Snell包络结构）刻画的最优策略。围绕这一形式化，我们证明了：（i）阶段一致、漂移感知的集中不等式，以及一个高概率正确的最坏情况认证规则，连同有限样本识别界；（ii）一个移动感知的信息价值停止规则，以及比较静态分析表明，更高的链路风险会降低继续探测的价值并扩大停止区域；（iii）在标记泊松接触到达下等待价值的闭式解，连同我们刻画其比较静态的搜索理论保留值；（iv）一个短视最优性定理，该定理表明，在足够波动（单调）的移动模式下，单步置信安全规则是最优策略的可靠替代，且永远不会过早停止。我们将该理论实例化为PROSE（用于交换的易逝证据保留值最优停止），一种轻量级、完全本地的策略，并描绘了恢复经典序贯决策问题的静态接触和无漂移极限。整个发展完全是分析性的。
英文摘要
Decentralised federated learning removes the aggregation server but makes collaboration dependent on transient peer availability. In mobile and intermittently connected systems, evaluating a promising peer consumes contact time and may cause the exchange opportunity itself to vanish, so that the evidence a learner gathers about a peer is perishable: it decays because links expire and because peer models drift while old measurements age. This paper develops a self-contained theory of optimal stopping for the resulting peer-selection problem. We formalise a receiver's within-contact decision as a finite-horizon Markov optimal-stopping problem with costly information acquisition and a future-arrival outside option, and prove that it admits an optimal policy characterised by a reservation value (Snell-envelope structure). Around this formulation we prove: (i) stage-uniform, drift-aware concentration and a maximin certification rule that is correct with high probability together with a finite-sample identification bound; (ii) a mobility-aware value of-information stopping rule and comparative statics showing that higher link hazard lowers the value of continued probing and enlarges the stopping region; (iii) a closed-form value of waiting under marked-Poisson contact arrivals, together with a search-theoretic reservation value whose comparative statics we characterise; and (iv) a myopic-optimality theorem establishing that, in sufficiently volatile (monotone) mobility regimes, the one-step confidence-safe rule is a sound surrogate for the optimal policy and never stops prematurely. We instantiate the theory as PROSE (Perishable-evidence Reservation-value Optimal Stopping for Exchange), a lightweight, fully local policy, and delineate the static contact and drift-free limits in which classical sequential decision problems are recovered. The development is entirely analytical.
Comments22 pages, 6 figures. Theory paper; no experiments
