Pathwise Information Certificates for Decentralized Adaptive Sensing
We study decentralized adaptive sensing, where multiple agents choose measurements from evolving local beliefs while exchanging information over a communication graph.
ProofPaper ↗
Key points
- 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.
Sources (1)
- [1]Pathwise Information Certificates for Decentralized Adaptive SensingarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 04:32 PM
We study decentralized adaptive sensing, where multiple agents choose measurements from evolving local beliefs while exchanging information over a communication graph.
We develop a pathwise certificate based on the Rényi--Chernoff information accumulated along the realized sensing trajectory.
Extractive summary: sentences quoted from the sources.