AoI-based Scheduling of Correlated Sources for Timely Inference

2025-09-01

AI Summary

This paper addresses real-time remote inference of multiple correlated time-varying sources under resource constraints: states of multiple dynamic targets must be estimated via bandwidth-limited channels, where inference accuracy critically depends on data freshness—quantified by Age of Information (AoI). Due to inter-source state correlation, the inference error penalty function of each source couples with the AoIs of other sources, rendering conventional restless multi-armed bandit (RMAB) decomposition techniques inapplicable. To overcome this, we propose a signal-agnostic online scheduling framework: first, we construct a decomposable approximate penalty function and derive a theoretical bound on the incurred estimation error; second, we design a Maximum Gain First online learning policy leveraging bandit feedback to achieve asymptotically optimal scheduling under unknown dynamics. Simulation results demonstrate that our approach significantly reduces inference error while maintaining excellent scalability.

Technology Category

• Machine Learning: Online Learning & Bandits
• Planning, Routing, and Scheduling: Scheduling under Uncertainty
• Intelligent Robots: State Estimation

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

We investigate a real-time remote inference system where multiple correlated sources transmit observations over a communication channel to a receiver. The receiver utilizes these observations to infer multiple time-varying targets. Due to limited communication resources, the delivered observations may not be fresh. To quantify data freshness, we employ the Age of Information (AoI) metric. To minimize the inference error, we aim to design a signal-agnostic scheduling policy that leverages AoI without requiring knowledge of the actual target values or the source observations. This scheduling problem is a restless multi-armed bandit (RMAB) problem with a non-separable penalty function. Unlike traditional RMABs, the correlation among sources introduces a unique challenge: the penalty function of each source depends on the AoI of other correlated sources, preventing decomposition of the problem into multiple independent Markov Decision Processes (MDPs), a key step in applying traditional RMAB solutions. To address this, we propose a novel approach by approximating the penalty function of each source and establish an analytical bound on the approximation error. We then develop scheduling policies for two scenarios: (i) full knowledge of the penalty functions and (ii) no knowledge of the penalty functions. For the case of known penalty functions, we present an upper bound on the optimality gap of our policy in the asymptotic regime. For the case of unknown penalty functions and signal distributions, we develop an online learning approach that utilizes bandit feedback to learn an online Maximum Gain First (MGF) policy. Simulation results demonstrate the effectiveness of our proposed policies in minimizing inference error and achieving scalability in the number of sources.

Problem

• Scheduling multiple correlated sources to minimize inference error
• Designing signal-agnostic policies using Age of Information metrics
• Solving non-separable restless multi-armed bandit with source correlation

Innovation

• AoI-based scheduling for correlated sources inference
• Approximating penalty function with analytical error bound
• Online learning MGF policy using bandit feedback