跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.26266 · v1

Cooling Noisy Population Protocols -- Vanishing-Gain Averaging and Localisation under Persistent Errors

首次提交 2026-11-19 23:35
版本更新 2026-11-19 23:35
雷达观测 2026-11-20 14:52
arXiv ↗PDF ↗

摘要

We study noise-tolerant coordination in anonymous population protocols whose agents interact in uniformly random pairs, maintain real-valued labels, and have no global clock. Each agent cools its updates using a gain γk=(k+1)−pγ_k=(k+1)^{-p} computed from its own local interaction counter. First, for pairwise averaging with independent communication errors drawn from a fixed centred finite-variance distribution, we prove convergence with probability 1 to a common finite random value for every 1/2<p≤11/2<p\le1, and derive convergence-rate exponents under the same assumptions. Second, for one-dimensional localisation with fixed non-degenerate Gaussian displacement errors, we show that the one-sided RightAlign rule rectifies centred noise and cannot stabilise; a signed update based on the relative-position discrepancy restores convergence to the true agents locations up to one finite random translation. Third, we analyse the setting in which both communication errors and displacement-measurement errors depend on the physical distance between the interacting devices. For additive independent Gaussian errors, the two sources combine into one centred effective error whose variance is the sum of the distance-dependent component variances. The signed updates protocol remains convergent for every fixed finite geometry, and the average combined variance determines the leading common-translation fluctuation. These results distinguish cooling-compatible signed corrections from one-sided updates that turn persistent noise into drift.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-19 23:35 · 最新观测版本

Cooling Noisy Population Protocols -- Vanishing-Gain Averaging and Localisation under Persistent Errors

We study noise-tolerant coordination in anonymous population protocols whose agents interact in uniformly random pairs, maintain real-valued labels, and have no global clock. Each agent cools its updates using a gain γk=(k+1)−pγ_k=(k+1)^{-p} computed from its own local interaction counter. First, for pairwise averaging with independent communication errors drawn from a fixed centred finite-variance distribution, we prove convergence with probability 1 to a common finite random value for every 1/2<p≤11/2<p\le1, and derive convergence-rate exponents under the same assumptions. Second, for one-dimensional localisation with fixed non-degenerate Gaussian displacement errors, we show that the one-sided RightAlign rule rectifies centred noise and cannot stabilise; a signed update based on the relative-position discrepancy restores convergence to the true agents locations up to one finite random translation. Third, we analyse the setting in which both communication errors and displacement-measurement errors depend on the physical distance between the interacting devices. For additive independent Gaussian errors, the two sources combine into one centred effective error whose variance is the sum of the distance-dependent component variances. The signed updates protocol remains convergent for every fixed finite geometry, and the average combined variance determines the leading common-translation fluctuation. These results distinguish cooling-compatible signed corrections from one-sided updates that turn persistent noise into drift.

查看此版本解读 →查看此版本原文 ↗