Fresh Enough to Decide: Age of Intelligence for Cost-Aware Model Synchronization in Dynamic IoT Systems
Paper · https://arxiv.org/abs/2611.09935
arXiv:2611.09935v1 Announce Type: new Abstract: Resource-constrained IoT devices cache learned models for real-time decisions, but frequent updates incur substantial bandwidth, energy, and service overhead. Because decision-relevant model differences need not grow with elapsed time, we define Age of Intelligence (AoInt) as a model-version-relative, client-specific, and action utility distortion, and formulate synchronization as a tradeoff between stale-decision regret and refresh cost. Furthermore, we develop Kullback-Leibler-aware AoInt Synchronization (KL-AoIntSync), which accumulates output-distribution changes using client-specific unlabeled probes, whereas Parameter-aware AoInt Synchronization (Param-AoIntSync) uses a server-broadcast scalar parameter change. Then, we establish pathwise guarantees with fixed client distributions, action sets, and utilities. The numerical results show that calibrated Param-AoIntSync reduces joint synchronization cost by 6.15% relative to an Instant-Parameters policy while performing comparably to KL-AoIntSync.
First seen by Oriel on .
AI summary
The paper introduces Age of Intelligence (AoInt) and two cost-aware model synchronization policies for IoT devices, balancing stale-decision regret against refresh costs.
- AoInt measures model-version-relative distortion in action utility for each client, rather than relying on elapsed time.
- KL-AoIntSync accumulates output-distribution changes using client-specific unlabeled probes; Param-AoIntSync uses a server-broadcast scalar parameter change.
- The authors establish pathwise guarantees under fixed client distributions, action sets, and utilities.
- Numerically, calibrated Param-AoIntSync reduces joint synchronization cost by 6.15% versus an Instant-Parameters policy and performs comparably to KL-AoIntSync.
#internet of things #model synchronization #age of intelligence #machine learning
Generated by gpt-5.6-sol. Check the original for details.
Aliases
| Source | External ID | URL |
|---|---|---|
| arXiv AI Papers | oai:arXiv.org:2611.09935v1 | https://arxiv.org/abs/2611.09935 Read discussion |